UIN (Universitas Islam Negeri) Sunan Kalijaga, Yogyakarta: E-Journal Fakultas Sains dan Teknologi
Not a member yet
1440 research outputs found
Sort by
Analysis of Public Sentiment Towards POLRI\u27s Performance using Naive Bayes and K-Nearest Neighbors
No full textUsing Twitter as a platform for sharing information includes tracking public perceptions of the performance of the Indonesian National Police (POLRI). Public sentiment assists as a gauge for evaluating POLRI\u27s operational capabilities and supports decision-making processes to enhance the organization\u27s reputation. However, raw public opinion data often requires careful analysis for decision-making. Hence, conducting sentiment analysis of Twitter data is crucial. This analytical process involves extracting and classifying opinions into neutral, positive, and negative sentiments. This study employs two distinct sentiment analysis methods: the Naive Bayes algorithm and the K-Nearest Neighbors. Analysis of 1285 tweets reveals prevailing satisfaction with POLRI\u27s performance, indicated by many positive sentiments. However, there is also a notable number of negative feelings. The assessment from confusion matrix results demonstrate that the Naive Bayes algorithm achieves 99.03% accuracy, while the K-Nearest Neighbors algorithm achieves 95.33% accuracy. By leveraging insights from public opinion data, POLRI can make more accurate and timely decisions, enabling it to better fulfill the community\u27s needs and expectations. This strategic use of data enhances service quality and bolsters POLRI\u27s favorable image among the public fosters more harmonious relationships and enhances public trust in law enforcement agencies
Deep Learning dalam Prediksi Kebiasaan Merokok di Inggris Guna Mendukung Kebijakan Kesehatan Masyarakat yang Lebih Efektif
No full textSmoking is a common practice throughout the world, where a person smokes and inhales the smoke produced from burning tobacco or other tobacco products. This action has become a significant global health issue because of the various health risks. This activity is often considered an addictive habit because nicotine, the psychoactive compound in tobacco, can cause physical and psychological dependence. This research applies Deep Learning methods to predict data on smoking habits in the UK. The dataset used in this research includes information about gender, age, marital status, highest level of education, nationality, ethnicity, income, and region. Through this research using Deep Learning methods, we can examine a complex data set that describes Smoking Habits in the UK. Based on trials with a dataset of 1,691 items, an accuracy of 78% was obtained. This research can provide important insights into the effectiveness of anti-smoking policies that have been implemented and help plan further actions to reduce the prevalence of smoking and its negative impact on society
Pengamanan Pesan Teks Menggunakan Affine Cipher dan Algoritma Goldbach Code
No full textPerkembangan informasi saat ini memiliki dampak negatif juga positif. Untuk menanggulangi adanya dampak negatif, diperlukan adanya kriptografi. Hal ini bertujuan agar keamanan pesan teks terjaga. Affine Cipher merupakan salah satu algoritma kriptografi simetris yang menggunakan (m) sebagai kunci multiplikatif dan (b) sebagai jumlah pergeseran pada saat proses enkripsi. Pada saat proses dekripsi menggunakan balikan dari kunci multiplikatif (m-1). Goldbach Code diasumsikan bahwa setiap bilangan bulat genap yang lebih besar dari empat merupakan penjumlahan dari dua bilangan prima. Penelitian ini memiliki dua tahapan, yaitu: proses enkripsi dan dekripsi. Pada penelitian ini, proses yang akan dilakukan bertujuan untuk mengamankan pesan teks yang diawali dengan mengenkripsikannya menggunakan Affine Cipher dan setelahnya akan dikompresi dengan menggunakan Algoritma Goldbach Code untuk menghasilkan cipherteks. Kemudian untuk mengembalikan pesan akan didekompresi dengan menggunakan Algoritma Goldbach Code dan dekripsi dengan menggunakan Affine Cipher. Dengan menggabungkan Affine Cipher dan Algoritma Goldbach code hasil dari proses pengamanan pesan teks akan lebih aman dikarenakan cipherteks yang dihasilkan memiliki panjang bit yang berbeda.
Kata kunci: Affine Cipher; Goldbach Code; Algoritma Kompresi; Kriptografi
-------------------------------------------------------------------------
The development of information today has both negative and positive impacts. To overcome the negative impact, cryptography is needed. This aims to maintain the security of text messages. Affine Cipher is a symmetric cryptography algorithm that uses (m) as the multiplicative key and (b) as the number of shifts during the encryption process. The decryption process uses the reciprocal of the multiplicative key (m-1). Goldbach Code assumes that every even integer greater than four is the sum of two prime numbers. This research has two stages, namely: encryption and decryption process. In this research, the process that will be carried out aims to secure text messages that begin by encrypting them using Affine Cipher and afterwards will be compressed using the Goldbach Code Algorithm to produce ciphertext. Then to restore the message, it will be decompressed using the Goldbach Code Algorithm and decrypted using Affine Cipher. By combining Affine Cipher and Goldbach Code Algorithm, the result of the text message security process will be more secure because the resulting ciphertext has a different bit length.
Keywords: Affine Cipher; Goldbach Code; Compression Algorithm; Cryptograph
Analisis Keamanan Sistem Informasi Pusaka Magelang Menggunakan Open Web Application Security Project (OWASP) Dan Information Systems Security Assessment Framework (ISSAF)
No full textSatu dasawarsa terakhir indonesia telah memiliki pengguna internet sebanyak 174 juta, peningkatan sebesar 17% internet usage dalam kurun waktu satu tahun. Peningkatan juga dipengaruhi oleh tumbuhnya 25 juta komunitas online selama bulan januari 2020. Lonjakan pengguna internet ini menunjukkan kesiapan indonesia dalam mengadopsi praktik E-government. Diskominfo magelang yang merupakan sebuah layanan pemerintahan daerah telah membuat kemajuan dalam memanfaatkan teknologi informasi dan komunikasi. Teknologi yang dihasilkan adalah sebuah web sistem informasi bernama “Pusaka Magelang”. Dalam memperkuat keamanan situs web pusaka magelang, maka diperlukan proses security assesment. Proses ini memerlukan sebuah framework OWASP dan ISSAF. Dengan menggunakan metode eksperimen, hasil pengujian menggunakan OWASP berhasil mengidentifikasi sebanyak 27 kerentanan dengan rincian 5 severity high, 5 severity medium 11 severity low dan 7 informational. Dari kerentanan yang ditemukan kemudian ditindak lanjuti dengan menilai tingkat risiko menggunakan OWASP Risk Rating diperoleh hasil skor likelihood sebesar 5,678 dan impact sebesar 5,9. Terakhir proses pengujian menggunakan kerangka ISSAF berhasil menemukan celah sensitive data exposure berupa info.php() yang bisa diakses secara publik sedangkan pengujian menggunakan teknik SQL Injection gagal dilakukan karena tidak berhasil mendapatkan database target.
Kata kunci: Internet Usage, Vulnerability Assessment, E-government, Vulnerability Assesment, OWASP, ISSAF.
-----------------------------------------
In the last decade Indonesia has had 174 million internet users, a 17% increase in internet usage in one year. The increase was also influenced by the growth of 25 million online communities during January 2020. This surge in internet users shows Indonesia\u27s readiness to adopt E-government practices. Diskominfo Magelang, which is a local government service, has made progress in utilizing information and communication technology. The resulting technology is a web information system called “Pusaka Magelang”. In strengthening the security of the Pusaka Magelang website, a security assessment process is required. This process requires an OWASP and ISSAF framework. Using the experimental method, the test results using OWASP successfully identified 27 vulnerabilities with details of 5 high severity, 5 medium severity 11 low severity and 7 informational. From the vulnerabilities found, it was then followed up by assessing the level of risk using the OWASP Risk Rating, resulting in a likelihood score of 5.678 and an impact of 5.9. Finally, the testing process using the ISSAF framework succeeded in finding sensitive data exposure in the form of info.php() which can be accessed publicly while testing using SQL Injection techniques failed because it did not succeed in getting the target database.
Keywords: Internet Usage, Vulnerability Assessment, E-government, Vulnerability Assesment, OWASP, ISSA
Comparison of Single Exponential Smoothing and Double Moving Average Algorithms to Forecast Beef Production
No full textBeef is considered a high-value commodity as it is an important source of protein. Interest in beef continues to rise. Beef production has risen sharply in the past decade, but declined by 7,240.68 tons in 2020 amid coronavirus lockdowns. After that, in 2021, production reached 16,381.81 tons and continued to increase in 2022 and 2023. A precise method is required to forecast beef production. One way to predict beef production in Jakarta is using the Single Exponential Smoothing and Double Moving Average methods. The two algorithms are compared to get the lowest error rate. The methodology used in this research is the SEMMA (Sample, Explore, Modify, Model, and Assess) methodology. According to SAS Institute Inc., there are five stages in developing a system using the SEMMA methodology. After analyzing using MAPE, it is found that the algorithm with the smallest error value is the Single Exponential Smoothing algorithm with a percentage in the monthly period of 16% while for the annual period, it is 27% compared to other algorithms. The forecasting is quite accurate because the MAPE value for each algorithm used has an error of less than 31%
Algoritma Decision Tree untuk Prediksi Deteksi Penyakit Kanker Payudara
No full textCancer is a deadly disease that is difficult to cure. Early cancer detection can be done through laboratory tests to identify the cancer type. Breast cancer is a type of cancer with initial symptoms in the form of a lump. Data mining and classification methods, such as decision trees with ID3 and C5.0 algorithms, are used to categorize breast cancer. The dataset used is Breast Cancer Coimbra, which was downloaded from UCI Machine Learning in 2018. ID3 has limitations in handling unstructured data and continuous attributes, while C5.0 is better. Both algorithms produce tree models with different levels of accuracy. This study shows that the C5.0 algorithm has the best classification results with 80% accuracy, 84.2% precision, 80% recall, and 80% F1 score. 80% accuracy shows the system\u27s classification ability, so the C5.0 model can be used to predict breast cancer
Klasterisasi Jumlah Penduduk Provinsi Jawa Timur Tahun 2021-2023 Menggunakan Algoritma K-Means
No full textUnderstanding the population data of a region is crucial for policy development and strategic planning. East Java Province, the second-largest province in Indonesia, has undergone significant population growth from 2021 to 2023. Uneven growth poses challenges in resource and infrastructure management. The K-Means algorithm clusters population data into several groups based on specific characteristics. The Elbow method is used to determine the optimal number of clusters, ensuring the accuracy of the analysis. This research aims to analyze and cluster the population distribution in each city in East Java Province, providing a more detailed and accurate depiction. The research findings reveal three significant clusters. Cluster 0 includes 21 towns, Cluster 1 comprises 4, and Cluster 2 encompasses 13. These findings have important implications for targeted development policy formulation at the city level in East Java Province. Additionally, this study contributes to the development of demographic analysis and population management, using valid methods and consistent results between RapidMiner and manual calculations. In conclusion, this research provides a solid foundation for more effective development policy formulation in East Java Province, offering essential information for sustainable population management
Implementasi Data Augmentation untuk Klasifikasi Sampah Organik dan Non Organik Menggunakan Inception-V3
No full textThe surge in global waste, particularly in Indonesia, with a total of 36.218 million tons per year, has become an urgent issue. Challenges in waste management are increasingly complex due to the lack of public understanding and awareness in classifying types of waste. One systemic approach to address waste classification issues involves the use of machine learning technology to categorize waste into two main types: organic and non-organic. The data used in this study comes from a Kaggle website dataset comprising 25,500 entries. This research employs a transfer learning approach with the Inception-V3 architecture and data augmentation implementation. Transfer learning is chosen for its proven performance in image data classification, while data augmentation is implemented to introduce diversity to the dataset. The research stages include business understanding, data preprocessing, data augmentation, data modelling, and evaluation. The results show that the use of transfer learning with the Inception-V3 approach and data augmentation implementation achieves an accuracy rate of 94%, which falls into the excellent category
SINTESIS ZEOLIT DARI ABU DASAR BATUBARA DAN APLIKASINYA SEBAGAI ADSORBEN MINYAK GORENG BEKAS
No full textTelah dilakukan sintesis zeolit dari abu dasar batubara dan digunakan sebagai adsorben untuk meningkatkan kualitas minyak goreng bekas. Zeolit disintesis dari abu dasar batubara dengan menggunakan metode peleburan hidrotermal. Adsorbsi zeolit hasil sintesis terhadap minyak goreng bekas diukur dengan menghitung angka asam, angka penyabunan dan angka peroksida. Berdasarkan hasil karakterisasi FTIR abu dasar batubara telah berhasil ditranformasi menjadi zeolit dengan mengamati serapan karakteristik IR zeolit. Hasil karakterisasi XRD menunjukkan bahwa sintesis zeolit dari abu dasar batubara menghasilkan beberapa jenis zeolit antara lain zeolit faujasit, zeolit faujasit –Y, zeolit cancrinit, dan zeolit Y namun, mayoritas zeolit yang terbentuk adalah zeolit faujasit. Hasil adsorbsi zeolit sintesis dalam minyak goreng memberikan pengaruh terhadap angka asam, angka penyabunan dan angka peroksida. Nilai angka asam turun dari 2,9172 mg OH/g menjadi 0,3366 mg OH/g; angka penyabunan naik dari 90,882 mg KOH/g menjadi 196,911 mg KOH/g; dan angka peroksida turun dari 20,8 meq/g menjadi 0,8 meq/g
Sentiment Analysis of TIMNAS Indonesia\u27s Participation in the Asian Cup U23 2024 on X Using Naive Bayes and SVM
No full textThis study aims to analyze the sentiment of the Indonesian public regarding the participation of the Indonesian National Team in the 2024 U-23 Asian Cup through the social media platform X. Sentiment analysis is crucial for understanding public perception and its impact on support for the national team. The research methodology involves collecting user comments on X related to the team\u27s performance during the tournament, followed by data cleaning. The dataset is manually labeled, with 80% used as training data for algorithmic model training and the remaining 20% as test data, classified using Naive Bayes and Support Vector Machine algorithms. The analysis results indicate that the SVM algorithm achieves a higher % accuracy rate of 95% compared to Naive Bayes, which achieves 87%. The majority of the 3367 opinions analyzed express positive or satisfactory sentiments towards the national team\u27s participation. However, there are fewer negative sentiments, highlighting areas requiring team management\u27s attention. This study provides valuable insights into public perception of the Indonesian National Team. Furthermore, these findings can inform policymakers and team managers\u27 decision-making to enhance the team\u27s quality and performance in the future