Garuda - Garba Rujukan Digital

Analisis aplikasi di Playstore berdasarkan Rating dan Type menggunakan Naive Bayes dan Logistic Regression Atmaja Jalu Narendra Kisma; Chyntia Raras Ajeng Widiawati; Suliswaningsih Suliswaningsih
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 10 No 2 (2023): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v10i2.4784

The use of mobile applications is increasingly important in daily life in the digital era. However, the abundance of application choices in the Play Store makes it difficult for users to choose the right application according to their needs. Not only that, application developers also have difficulty finding the most liked ratings by users and the type of application that is widely downloaded. This research aims to find a solution to the problems of users and developers by comparing the performance of Naive Bayes and Logistic Regression algorithms in classifying Google Play Store application data based on ratings and the type of application that is most downloaded by users. The results show that both algorithms have a high level of accuracy, but Naive Bayes has a higher level of accuracy than Logistic Regression. Naive Bayes obtains an accuracy rate of 92.63% while Logistic Regression obtains an accuracy rate of 92.60%. This research provides guidance for users to choose the right algorithm in classifying Google Play Store application data. However, these results are based on the data used in a particular study, so they cannot be generalized to all situations and datasets. Other factors such as data quality and proper feature selection can also affect algorithm performance. In addition, this research also shows that the type of application that is most downloaded by users on the Google Play Store is a free application. This can be input for developers to develop types of applications that are favored by users. This research also shows the results of application ratings, where an application named Life Made WI-FI Touchscreen Photo Frame with the photo editing category gets a very high rating. These results can be input or references for application developers to create even better applications in the future..

Detection of Indonesian Food to Estimate Nutritional Information Using YOLOv5 Gina Cahya Utami; Chyntia Raras Widiawati; Pungkas Subarkah
Teknika Vol 12 No 2 (2023): Juli 2023
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v12i2.636

Currently, the development of online food delivery service applications is very popular. The application offers convenience in finding and fulfilling food needs. That circumstance has an impact such as not controlling the type and amount of food consumed. Therefore, to maintain a healthy lifestyle, people need to eat healthy and nutritious food. The goal of this research is to build a model using the YOLOv5 model that can detect images of Indonesian food so that nutritional estimation can then be carried out by taking information per serving data sourced from the FatSecret Indonesia website. The methods of this research include data collection, data pre-processing, training, testing, evaluation, image detection, and model export. The outcome of this research is an object detection model that is ready to be implemented in android applications or websites to detect images of Indonesian food which can be estimated for each nutrient. Based on the detection results, 98.6% for an average of a curacy, 95% for precision, 95.3% for recall, and 95% for F1-Score were obtained. The results of the detection are then used to estimate nutrition by taking information per portion from the FatSecret Indonesia website. From the experiments that were carried out on seven pictures of Indonesian food, the estimation was carried out well by displaying various nutritional information including energy, protein, fat, and carbohydrates.

Pelatihan Operasi Dasar Komputer dan Aplikasi Ms. Word Bagi Kelompok PKK Desa Ketenger Chyntia Widiawati; Aulia Shafira Tri Damayanti; Luthfi Khaerunnisa; Delia Oktaviana Azzahra
ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT Vol 7, No 1 (2024): JANUARI 2024
Publisher : LPPM UNIVERSITAS DIAN NUSWANTORO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/ja.v7i1.1626

Kemampuan mengoperasikan komputer khususnya pada penggunaan Ms. Word saat ini merupakan hal penting yang dapat menunjang berbagai kegiatan tak terkecuali bagi anggota dan pengurus PKK Desa Ketenger. Beberapa masalah yang kerap dihadapi oleh kelompok PKK Desa Ketenger adalah keterbatasan dalam mengoperasikan komputer dan menggunakan aplikasi Ms. Word untuk membuat surat undangan kegiatan, proposal dan laporan kegiatan PKK. Kegiatan pendampingan dapat menjadi salah satu alternatif solusi untuk menyelesaikan beberapa permasalahan tersebut khususnya pada pengoperasian komputer dan penggunaan Aplikasi Ms. Word. Pendampingan ini diberikan kepada seluruh anggota dan pengurus Kelompok PKK Desa Ketenger. Pelaksanaan kegiatan pelatihan ini sangat membantu kelompok PKK Desa Ketenger dan meningkatkan keterampilan dalam menggunakan komputer dan Ms. Word.

Optimization of Perfume Sales through Data Mining with K-Means Algorithm Rahayu, Mia Setya; Yunita, Ika Romadoni; Widiawati, Chyntia Raras Ajeng
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7922

This time the research used the abc Parfume shop as the research site. This store offers various types of perfumes with different variants because, there are many variants so that not all perfumes sell quickly and some even do not sell at all. To recap sales and expenses in abc stores is still done manually so that it often causes mistakes in increasing stock and hinders the development of marketing strategies. The data that has been collected should be used as a decision-making system to solve business problems. For this reason, the author conducts data mining calculations that are carried out automatically in the hope of providing effective and maximum results in analyzing perfume sales at abc perfume stores. The application of Data Mining in collaboration with the K-Means Algorithm has proven to provide the best analysis and be a solution in developing the perfume business. The results of this study divided the clustering into three clusters for the final result there were nine cluster projects with nine products, cluster two with three products, and cluster three or the last cluster with thirteen products from a total of twenty-five data collected. The results of each cluster are grouped such as Cluster One which is the best seller, Cluster two is grouped to the middle position because sales are stable, while products in Cluster Cluster three are less in demand. This research was successfully conducted and contributed to a deeper understanding of the K-Means algorithm.

Volatility Analysis of Cryptocurrencies using Statistical Approach and GARCH Model a Case Study on Daily Percentage Change Sarmini, Sarmini; Widiawati, Chyntia Raras Ajeng; Febrianti, Diah Ratna; Yuliana, Dwi
Journal of Applied Data Sciences Vol 5, No 3: SEPTEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i3.261

Cryptocurrency has become a significant subject in the global financial market, attracting investors and traders with its high volatility and profit potential. This study analyzes the daily volatility and GARCH volatility of six major cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), Litecoin (LTC), USD Coin (USDC), Tether (USDT), and Ripple (XRP). Daily percentage change data and GARCH volatility are analyzed over specific time periods. The analysis reveals that Bitcoin (BTC) has an average daily percentage change of 0.366%, while Ethereum (ETH) has 0.376%. Litecoin (LTC) shows a daily percentage change of 0.166%, whereas USD Coin (USDC) and Tether (USDT) have very low daily percentage changes, nearly approaching zero. In terms of GARCH volatility, Ethereum (ETH) stands out with a volatility of 0.198, followed by Bitcoin (BTC) with a volatility of 0.121. The study's results indicate that cryptocurrencies are vulnerable to extreme price fluctuations, evidenced by their asymmetry distribution and kurtosis. Volatility correlation analysis reveals significant relationships, important for risk management and portfolio diversification. These findings contribute to understanding cryptocurrency volatility characteristics and aid stakeholders in making informed investment decisions.

Implementasi Algoritma Logistic Regression pada Pembuatan Website Sederhana untuk Prediksi Penyakit Jantung Chyntia Raras Ajeng Widiawati; Lisa Nurazizah; Ika Romadoni Yunita
Infotekmesin Vol 15 No 1 (2024): Infotekmesin: Januari, 2024
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v15i1.2048

Heart disease is a deadly disease, early recognition is important to prevent the fairly high death rate due to this disease. There are various ways to detect heart disease early, one of which is by utilizing machine learning. In this research, the author uses secondary data, namely data taken from the website www.kaggle.com for the prediction process. The amount of data used was 297 data, with details of 160 data not detecting heart disease, and 137 data detecting heart disease. Apart from making predictions from heart disease patient data using the logistic regression algorithm, this research also implements the model that has been created on the website. The results of implementing the logistic regression algorithm in this research are an accuracy value of 0.9, precision of 0.92, recall of 0.86, and f1-score of 0.89. After measuring using these 4 parameters, the model that has been created is then implemented into a simple website using the Rapid Application Development (RAD) method.

Predicting Network Performance Degradation in Wireless and Ethernet Connections Using Gradient Boosting, Logistic Regression, and Multi-Layer Perceptron Models Widiawati, Chyntia Raras Ajeng; Sarmini, Sarmini; Yuliana, Dwi
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.519

This study explores predicting network performance degradation in wireless and Ethernet connections using three machine learning algorithms: XGBoost, Logistic Regression, and Multi-Layer Perceptron (MLP). Key metrics, including accuracy, precision, recall, F1-score, and AUC-ROC, were employed to evaluate model performance. The MLP classifier achieved the highest accuracy (98.7%) and AUC-ROC (0.9998), with a precision of 1.0000 and recall of 0.8622, resulting in an F1-score of 0.9260. Logistic Regression provided reasonable baseline performance, with an accuracy of 93.67%, AUC-ROC of 0.9565, and an F1-score of 0.5992, but struggled with non-linear dependencies. XGBoost showed limited utility in detecting degradation events, achieving an F1-score of 0 despite a perfect AUC-ROC (1.0), indicating sensitivity to imbalanced data. Through hyperparameter tuning, MLP demonstrated robustness in capturing complex patterns in network latency metrics (local_avg and remote_avg), with remote_avg emerging as the most predictive feature for identifying degradation across both network types. Visualizations of latency dynamics demonstrate the higher predictive relevance of remote latency (remote_avg) in both network types, where spikes in this metric are closely associated with degradation. The findings underscore the effectiveness of using latency metrics and machine learning to anticipate network issues, suggesting that MLP is particularly well-suited for real-time, predictive network monitoring. Integrating such models could enhance network reliability by enabling proactive intervention, crucial for sectors reliant on continuous connectivity. Future work could expand on feature sets, explore adaptive thresholding, and implement these predictive models in live network environments for real-time monitoring and automated response.

Analisis Komparatif Linear Regression, Random Forest, dan Gradient Boosting untuk Prediksi Banjir Maulita, Ika; Widiawati, Chyntia Raras Ajeng; Wahid, Arif Mu'amar
Jurnal Pendidikan dan Teknologi Indonesia Vol 4 No 8 (2024): JPTI - Agustus 2024
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.599

Penelitian ini mengevaluasi tiga model machine learning—Linear Regression, Random Forest Regressor, dan Gradient Boosting Regressor—untuk memprediksi probabilitas banjir di India, dengan tujuan meningkatkan akurasi prediksi dan mendukung strategi mitigasi risiko banjir. Kinerja model dievaluasi menggunakan metrik Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), dan ????2. Hasil penelitian menunjukkan bahwa Linear Regression dan Gradient Boosting Regressor memiliki kinerja yang hampir setara, dengan MAE dan RMSE yang kompetitif. Namun, Linear Regression sedikit unggul dalam menjelaskan variabilitas probabilitas banjir berdasarkan nilai ????2. Sebaliknya, Random Forest Regressor menunjukkan kinerja yang lebih rendah, yang kemungkinan disebabkan oleh overfitting atau kurang optimalnya penyetelan parameter. Penelitian ini memberikan kontribusi penting terhadap peningkatan akurasi sistem peringatan dini dan pengelolaan risiko banjir berbasis data. Dengan menganalisis faktor-faktor utama yang memengaruhi probabilitas banjir, penelitian ini menawarkan wawasan yang dapat mendukung perencanaan intervensi yang lebih efektif, seperti pengelolaan sungai yang lebih baik dan perencanaan tata ruang perkotaan yang adaptif. Saran untuk penelitian mendatang meliputi eksplorasi algoritma tambahan, termasuk pendekatan pembelajaran mendalam, penerapan rekayasa fitur lanjutan, serta optimalisasi model menggunakan alat Automated Machine Learning (AutoML). Temuan ini berkontribusi pada pengembangan metode prediksi banjir yang lebih akurat dan efisien, serta memperkuat upaya mitigasi risiko banjir di masa depan.

Optimization of Perfume Sales through Data Mining with K-Means Algorithm Rahayu, Mia Setya; Yunita, Ika Romadoni; Widiawati, Chyntia Raras Ajeng
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7922

This time the research used the abc Parfume shop as the research site. This store offers various types of perfumes with different variants because, there are many variants so that not all perfumes sell quickly and some even do not sell at all. To recap sales and expenses in abc stores is still done manually so that it often causes mistakes in increasing stock and hinders the development of marketing strategies. The data that has been collected should be used as a decision-making system to solve business problems. For this reason, the author conducts data mining calculations that are carried out automatically in the hope of providing effective and maximum results in analyzing perfume sales at abc perfume stores. The application of Data Mining in collaboration with the K-Means Algorithm has proven to provide the best analysis and be a solution in developing the perfume business. The results of this study divided the clustering into three clusters for the final result there were nine cluster projects with nine products, cluster two with three products, and cluster three or the last cluster with thirteen products from a total of twenty-five data collected. The results of each cluster are grouped such as Cluster One which is the best seller, Cluster two is grouped to the middle position because sales are stable, while products in Cluster Cluster three are less in demand. This research was successfully conducted and contributed to a deeper understanding of the K-Means algorithm.

Program pendampingan penulisan ilmiah dan eksplorasi kesenjangan penelitian menggunakan teknologi kecerdasan buatan bagi Dosen Fakultas Ilmu Komputer Universitas Amikom Purwokerto Widiawati, Chyntia Raras Ajeng; Utomo, Fandy Setyo; Saputro, Rujianto Eko; Sarmini, Sarmini; Adiya, Az Zahra Dwi Nur; Ilham, Rifqi Arifin; Hartini, Sri
SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan Vol 8, No 4 (2024): December
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jpmb.v8i4.26890

AbstrakPermasalahan yang dihadapi oleh mitra sasaran Fakultas Ilmu Komputer (FIK) Universitas Amikom Purwokerto adalah rendahnya jumlah dosen yang memiliki gelar doktor yang berperan penting untuk meningkatkan kualitas pendidikan dan penelitian. Berdasarkan data FIK, dari 72 dosen, hanya 6 yang memiliki gelar doktor. Rendahnya jumlah doktor ini disebabkan karena dosen kesulitan dalam menentukan tema penelitian yang tepat dan relevan dengan kepakaran mereka, kesulitan menemukan dan merumuskan kesenjangan penelitian, serta kesulitan dalam merumuskan inovasi dan kebaruan riset. Berdasarkan permasalahan tersebut, kami memberikan solusi menyelenggarakan program Bootcamp Doktoral: Penulisan ilmiah dan identifikasi kesenjangan penelitian menggunakan teknologi kecerdasan buatan. Target yang diharapkan dari program ini, yakni dosen di lingkungan fakultas ilmu komputer dapat meningkatkan kompetensi akademik, mengembangkan jaringan profesional, meningkatkan keterampilan penelitian dan penulisan publikasi, memperoleh motivasi dan inspirasi untuk studi lanjut S3, mengembangkan soft skill, serta mampu beradaptasi dengan tren teknologi terbaru. Berdasarkan target luaran yang telah ditetapkan, metode pengabdian masyarakat yang digunanakan dalam program ini mencakup 3 tahap utama, yaitu tahap persiapan kegiatan, implementasi kegiatan, dan pelaporan kegiatan. Hasil evaluasi pelaksanaan program pendampingan melalui umpan balik peserta pada hari selasa, 20 Agustus 2024 secara daring diperoleh hasil bahwa seluruh peserta webinar dapat memahami pengoperasian tools berbasis teknologi kecerdasan buatan untuk penulisan ilmiah, dan memahami etika penggunaan teks atau data dari hasil tools kecerdasan buatan dalam konteks penelitian. Kata kunci: pendampingan; kecerdasan buatan; penulisan ilmiah; penelitian; doktoral AbstractThe problem faced by the target partners of the Faculty of Computer Science Universitas Amikom Purwokerto is the low number of lecturers who have doctoral degrees who play an essential role in improving the quality of education and research. The low number of doctors is caused by lecturers having difficulty determining the correct and relevant research themes with their expertise, difficulty finding and formulating research gaps, and difficulty formulating innovation and research novelty. Based on these problems, we provide a solution to organize a Doctoral Bootcamp program: Scientific writing and identifying research gaps using artificial intelligence technology. The expected target of this program is that lecturers in the faculty of computer science can improve their academic competence, develop professional networks, improve research skills and publication writing, gain motivation and inspiration for further doctoral studies, develop soft skills, and be able to adapt to the latest technological trends. Based on the set output targets, the community service method used in this program includes three main stages: the activity preparation stage, activity implementation, and activity reporting. The results of the evaluation of the implementation of the mentoring program through participant feedback showed that all webinar participants were able to understand the operation of artificial intelligence technology-based tools for scientific writing and understand the ethics of using text or data from the results of artificial intelligence tools in the context of research. Keywords: mentoring; artificial intelligence; scientific writing; research; doctoral

Title

Found 25 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 25 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 25 Documents
Search