cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
mib.stmikbd@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
JURNAL MEDIA INFORMATIKA BUDIDARMA
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Budi Darma
ISSN : 26145278     EISSN : 25488368     DOI : http://dx.doi.org/10.30865/mib.v3i1.1060
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering
Decission Support System, Expert System, Informatics tecnique, Information System, Cryptography, Networking, Security, Computer Science, Image Processing, Artificial Inteligence, Steganography etc (related to informatics and computer science)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 1,182 Documents
 104   105   106   107   108 
Improving Infant Cry Recognition with CNNs and Imbalance Mitigation Indrawan, Michael; Luthfiarta, Ardytha; Fahreza, Muhammad Daffa Al; Rafid, Muhammad
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7370

Abstract

The classification of baby cries using machine learning is essential for developing automated systems that can assist caregivers in identifying and responding to the needs of infants promptly and accurately. This study aims to improve upon previous research relating to the Cry Baby Dataset, which has highly imbalanced data. We combine oversampling and undersampling techniques using SMOTE and ENN, along with data augmentation through pitch shifting and noise addition to address the data imbalance issue. The processed data was then modeled using Convolutional Neural Networks (CNN). The study yielded an overall accuracy of 88%, with balanced accuracy observed across all classes, effectively mitigating data imbalance. This represents a notable advancement compared to previous research, which often encountered challenges with unbalanced accuracies across classes. The classes identified include recordings of baby cries attributed to belly pain caused by colic, recordings related to burping, recordings associated with discomfort or other symptoms, recordings of hungry baby cries, and recordings indicating fatigue or the need for sleep. This shows a significant improvement from previous studies, which had very unbalanced accuracy for each class.
Analisis Sentimen Calon Presiden 2024 di Media Sosial X Menggunakan Naive Bayes dan SMOTE Sunata, Muhamad Hafidz Ardian; Irwiensyah, Faldy; Hasan, Firman Noor
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.v8i3.7708

Abstract

In the era of digital advancement, the utilization of social media has surged, enabling individuals to express their viewpoints openly. This research underscores the utilization of social media platform X as the primary avenue for users to express their opinions, particularly on political matters, notably within the framework of the presidential election. Sentiment analysis techniques, specifically employing the Naïve Bayes algorithm and the Synthetic Minority Oversampling (SMOTE) method, have been the central focus of inquiry to infer people's inclinations toward presidential candidates. Despite numerous antecedent studies, deficiencies persist in terms of precision and data imbalance. This study endeavors to enhance the efficacy of sentiment analysis by integrating the Naïve Bayes approach with SMOTE. By scrutinizing tweets on social media X spanning from December 12, 2023, to March 31, 2024, the data is categorized into positive and negative sentiments. The findings reveal that employing SMOTE bolstered accuracy to 88% for the Ganjar-Mahfud dataset, whereas accuracy without SMOTE languished at approximately 69% for the Anies-Imin dataset. Out of 1589 tweets conveying positive sentiments, approximately 27.7% were directed towards Anies-Imin, 28.7% towards Prabowo-Gibran, and 43.5% towards Ganjar-Mahfud. The preponderance of negative sentiments was aimed at Anies-Imin (41.5%) and Prabowo-Gibran (40.8%).
Perbaikan Akurasi Naïve Bayes dengan Chi-Square dan SMOTE Dalam Mengatasi High Dimensional dan Imbalanced Data Banjir Rivaldo, Vito Junivan; Siswa, Taghfirul Azhima Yoga; Pranoto, Wawan Joko
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.v8i3.7886

Abstract

Floods are one of the natural disasters that frequently occur in Indonesia. The city of Samarinda is affected by floods every year, resulting in significant losses. The data used in this study comes from the Regional Disaster Management Agency (BPBD) and the Meteorology, Climatology, and Geophysics Agency (BMKG) for the years 2021-2023 in Samarinda. This data includes 11 attributes and 1095 records. Previous studies on data mining related to floods have been conducted. However, issues arise with high-dimensional data and data imbalance. High dimensionality leads to overfitting and reduced accuracy, while imbalanced data causes overfitting to the majority class and inaccurate representation. This study aims to improve the accuracy of the Naive Bayes algorithm in predicting high-dimensional and imbalanced flood data. The approach involves using the Chi-Square feature selection technique and oversampling with the Synthetic Minority Over-sampling Technique (SMOTE). Chi-Square is used to find optimal features for predicting floods and to enhance the accuracy of the Naive Bayes algorithm in predicting high-dimensional and imbalanced flood data. The validation method used is 10-fold cross-validation, and a confusion matrix model is employed to calculate accuracy values. The results of the study show that Chi-Square can identify four best features: average humidity (rh_avg), rainfall (rr), maximum wind direction (ddd_x), and most frequent wind direction (ddd_car). The use of the Naive Bayes algorithm with SMOTE achieved an accuracy of 71.58%. However, after applying Chi-Square feature selection, the accuracy dropped to 60.82%. This decline is attributed to the reduced number of minority classes after feature selection. Therefore, Chi-Square feature selection is not sufficiently effective in improving the accuracy of Naive Bayes on high-dimensional data.
Klasterisasi Perguruan Tinggi LLDIKTI V Berdasarkan Indikator Kinerja Utama dan PDDIKTI Menggunakan K-Means Clustering Fatmawaty, Virdiana Sriviana; Riadi, Imam; Herman, Herman
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7497

Abstract

Pertumbuhan jumlah perguruan tinggi yang terus meningkat menjadi salah satu faktor krusial untuk memastikan mutu pendidikan tinggi agar berdaya saing. Komposisi perguruan tinggi di Provinsi Daerah Istimewa Yogyakarta terdiri atas 77% Perguruan Tinggi Swasta (PTS) dan sisanya adalah Perguruan Tinggi Negeri (PTN). Masing-masing perguruan tinggi memiliki Indikator Kinerja Utama (IKU) yang wajib dilaporkan dan dipenuhi, serta melakukan pendataan aktivitas pembelajarannya pada Pangkalan Data Pendidikan Tinggi (PDDIKTI). Data IKU dan data PDDIKTI ini menjadi  bahan evaluasi dan analisis untuk menentukan baseline dalam aktivitas pembinaan di LLDikti Wilayah V khususnya bagi PTS. Salah satu model analisis yang dapat dilakukan adalah dengan metode klasterisasi. Metode ini biasa digunakan pada data mining untuk mengelompokkan data berdasarkan kesamaan karakteristik data. Penelitian ini melakukan klasterisasi PTS di LLDIKTI Wilayah V menggunakan algoritma K-Means Custering. Hasil penelitian ini menunjukkan bahwa berdasarkan kesamaan karakteristik data IKU dan data PDDIKTI terbentuk empat klaster PTS, yaitu klaster 1 terdiri dari 4 PTS, klaster 2 terdiri dari 46 PTS, klaster 3 terdiri dari 21 PTS, dan klaster 4 terdiri dari 33 PTS.  Hasil analisis ini akan sangat bermanfaat bagi LLDIKTI Wilayah V dalam melakukan fungsi pembinaan kepada PTS.
Segmentasi Pelanggan Menggunakan Fuzzy C-Means dan FP-Growth Berdasarkan Model LRFM untuk Rekomendasi Produk Rahmah, Astriana; Afdal, M
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.v8i3.7737

Abstract

Bazmart Pelalawan is a part of the National Zakat Agency (BAZNAS) program in Pelalawan Regency, which has implemented strategies to retain customers. However, these strategies have not yet succeeded in fully understanding customer characteristics, resulting in a decline in customer trust and their willingness to shop again. Additionally, Bazmart lacks proper guidelines for offering products that meet customer needs. This research aims to enhance product recommendations by integrating LRFM analysis into data mining techniques. The parameters considered include customer LRFM values, customer segmentation, and products frequently purchased together over a year of transaction data. Fuzzy C-Means and FP-Growth algorithms were used for segmentation and association analysis. The segmentation results identified two customer clusters with a Davies-Bouldin Index (DBI) value of 0.628, indicating good cluster quality. In the association analysis, a minimum support (minsup) of 30% and a minimum confidence (mincof) of 70% were used, resulting in 8 rules for cluster 1 and 17 rules for cluster 2. From the two association pattern results, the highest rules were obtained, namely in Drinks and Snacks and Bread with a support value of 0.426 and a confidence value of 0.926 resulting in a value of 0.394. These rules provide insights that Bazmart Pelalawan can use to develop more effective and targeted direct marketing strategies for each customer cluster. Thus, this research is expected to help Bazmart Pelalawan better understand customer characteristics and improve customer loyalty through more targeted product recommendations.
Optimizing Sentiment Analysis of Working Hours Impact on Generation Z’s Mental Health Using Backpropagation Farsya, Nabila Zibriza; Luthfiarta, Ardytha; Maharani, Zahra Nabila; Ganiswari, Syuhra Putri
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.v8i3.7827

Abstract

The topic of working hours' impact, Generation Z, and mental health are discussions that are often found on social media such as X (used to be Twitter). The sentiment analysis addressing these topics is needed to find out people’s opinions regarding these topics. It could also be helpful as a consideration for the decision-making process for related topics research. Therefore, this research aims to improve the accuracy of the model generated by the previous sentiment analysis research regarding the working hours’ impact on Gen Z’s mental health. The contribution of this research is by building a robust Backpropagation Neural Network model and utilizing SMOTETomek to achieve higher accuracy. This research compared two oversampling techniques for data balancing: SMOTE and SMOTETomek. The result shows that this research has successfully outperformed the baseline research with the best accuracy of 91% using SVM by generating the best accuracy of 93.01% with SMOTETomek. For comparison, SMOTETomek has outperformed SMOTE by generating the best accuracy of 93.01%, while the best accuracy generated with SMOTE is 92.26%. It indicates that in the case of Indonesian text sentiment analysis of this research, SMOTETomek has a better effect compared to SMOTE.
Analisis Sentimen Opini Terhadap Tools Artificial Intelligence (AI) Berdasarkan Twitter Menggunakan Algoritma Naïve Bayes Oktavia, Ingrid; Isnain, Auliya Rahman
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7524

Abstract

This research aims to analyze public sentiment towards artificial intelligence (AI) tools via the Twitter platform using the Naive Bayes classifier algorithm. Twitter is a popular social media platform for sharing opinions and thoughts, making it suitable for sentiment analysis. Sentiment analysis is the process of analyzing and understanding opinions, attitudes, or feelings contained in text, such as tweets, product reviews, or other social media posts. The problems discussed in sentiment analysis can vary depending on the context. Tests carried out using the Naïve Bayes Classifier algorithm can conclude that the data collected was 2119. In this research, there are several steps that must be taken to analyzethe data, starting with crawling, labeling, preprocessing, splitting data, dividing test data, and training data, and finally applying the Naïve Bayes Classifier Algorithm. The results of the data analysis were divided into two categories: positive and negative, with 58.41% positive data and 12.43% negative data. In the analysis experiment, the Naïve Bayes accuracy value reached 79.41%, with a precision of 88% and a recall of 88%. The aim of the results of this research is to examine the public's response regarding artificial intelligence tools using the Naïve Bayes Classifier Algorithm to provide better sentiment results. So many see AI as a technology that carries great potential to improve human life. On the other hand, there are concerns about AI's negative impact on employment, privacy, and even its potential to take over human control. Ethical concerns also arise regarding the use of AI in decision-making that can affect human lives without adequate control. So artificial intelligence tools can be accepted by society because they have many benefits. Therefore, sentiment analysis and natural data processing use the Python programming language to categorize user comment data through a breakdown process.
Komparasi Metode LSTM dan GRU dalam Memprediksi Harga Saham Meri Aryati, Ni Wayan; Wiguna, I Komang Arya Ganda; Putri, Ni Wayan Suardiati; Widiartha, I Komang Kurniawan; Ginantra, Ni Luh Wiwik Sri Rahayu
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7342

Abstract

The rapid development of technology has an impact on the economy of society, one of which is investing in stocks. Stocks are evidence of ownership of an individual's assets in a company. However, stock prices have very high levels of fluctuation, requiring accurate methods to assist in predicting stock prices. LSTM and GRU were chosen for their intrinsic ability to handle long-term and short-term problems in time series data. LSTM has a complex memory structure that allows decision-making based on long and short-term information. Meanwhile, GRU has a simpler structure with a focus on gate mechanisms to control information flow, resulting in lighter and faster models. Therefore, this study will compare two RNN methods, Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU), in predicting stock prices using MAPE and RMSE evaluation metrics. The combination of parameters used to evaluate the MAPE and RMSE values in this study includes learning rate, timestamps, batch size, and epoch. The results of this study show that the GRU method is more accurate compared to the LSTM method. This is evidenced by the evaluation results of the LSTM method with the lowest MAPE value of 2.42% and the lowest RMSE value of 0.01807, while the evaluation results of the GRU method with the lowest MAPE value of 2.14% and the lowest RMSE value of 0.01775. The combination of parameters used in this study also has an influence on the final MAPE and RMSE results, especially in the use of learning rates of 0.001 and 0.0001. Therefore, it can be concluded in this study that the GRU method is more accurate and effective compared to the LSTM method in predicting stock prices.
Analisis Metode Smoote pada Klasifikasi Penyakit Jantung Berbasis Random Forest Tree Yulianto, Satria Pradana Rizki; Fanani, Ahmad Zainul; Affandy, Affandy; Aziz, Mochammad Ilham
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.v8i3.7712

Abstract

Cardiovascular disease is the number one cause of death globally. Cardiovascular disease is a disease caused by impaired function of the heart and blood vessels. At present, there are many predictive tools that use machine learning as a basis, including predictions on heart disease in particular. There are many methods in machine learning to predict heart disease, as well as many parameters to look for to find the highest level of accuracy. This study, aims to obtain the best methods and parameters for the classification of heart disease.
Toxicity, Sentiment, and Social Network Analysis (SNA) of Borneo Death Blow Video Documentary Reviews Singgalen, Yerik Afrianto
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7633

Abstract

The study aimed to evaluate sentiment classification models using toxicity scores and to conduct Social Network Analysis (SNA) to understand network dynamics. The research used CRISP-DM methodology to comprehensively analyze sentiment classification models and toxicity scores. It utilized various machine learning algorithms, including Decision Tree (DT), Support Vector Machine (SVM), and Naive Bayes Classifier (NBC), with Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance. In addition, Social Network Analysis (SNA) was conducted to examine network properties and dynamics. The findings revealed varying toxicity scores, ranging from 0.12409 to 0.98808, across different categories, such as general toxicity, severe toxicity, identity attacks, insults, profanity, and threats. Evaluation of sentiment classification models indicated that the SVM model with SMOTE achieved the highest accuracy of 92.57% +/- 1.17% (micro average: 92.57%), followed by the NBC model with an accuracy of 78.24% +/- 1.30% (micro average: 78.24%), and the DT model with an accuracy of 61.16% +/- 1.20% (micro average: 61.16%). Despite variations in model performance, the SVM model consistently demonstrated robust performance across various evaluation metrics. Furthermore, the SNA findings provided insights into network structural characteristics, including Average Degree, Average Weighted Degree, Diameter, Radius, and Average Path Length, facilitating a comprehensive understanding of network organization and behavior. These findings contribute to advancing the understanding of sentiment analysis models and network dynamics in digital environments.

Page 106 of 119 | Total Record : 1182

 104   105   106   107   108 

Filter by Year

2017 2024


Reset
Filter By Issues
All Issue Vol 8, No 3 (2024): Juli 2024 Vol 8, No 2 (2024): April 2024 Vol 8, No 1 (2024): Januari 2024 Vol 7, No 4 (2023): Oktober 2023 Vol 7, No 3 (2023): Juli 2023 Vol 7, No 2 (2023): April 2023 Vol 7, No 1 (2023): Januari 2023 Vol 6, No 4 (2022): Oktober 2022 Vol 6, No 3 (2022): Juli 2022 Vol 6, No 2 (2022): April 2022 Vol 6, No 1 (2022): Januari 2022 Vol 5, No 4 (2021): Oktober 2021 Vol 5, No 3 (2021): Juli 2021 Vol 5, No 2 (2021): April 2021 Vol 5, No 1 (2021): Januari 2021 Vol 4, No 4 (2020): Oktober 2020 Vol 4, No 3 (2020): Juli 2020 Vol 4, No 2 (2020): April 2020 Vol 4, No 1 (2020): Januari 2020 Vol 3, No 4 (2019): Oktober 2019 Vol 3, No 3 (2019): Juli 2019 Vol 3, No 2 (2019): April 2019 Vol 3, No 1 (2019): Januari 2019 Vol 2, No 4 (2018): Oktober 2018 Vol 2, No 3 (2018): Juli 2018 Vol 2, No 2 (2018): Apriil 2018 Vol 2, No 1 (2018): Januari 2018 Vol 1, No 3 (2017): September 2017 Vol 1, No 2 (2017): Juni 2017 Vol 1, No 1 (2017): Maret 2017 More Issue