Jurnal Teknologi Informasi, Komputer, dan Aplikasinya (JTIKA )

RANCANG BANGUN SISTEM MONITORING PROSES PEMBUATAN KOMPOS DARI SAMPAH RUMAH TANGGA BERBASIS INTERNET OF THINGS (IoT)

2025-03-22T03:58:32+08:00

Household waste is one of the largest contributors to environmental waste, reaching 39.63% of the total 19.45 million tonnes of waste produced in Indonesia in 2022 from National Waste Management Information System (SIPSN) data. Waste is a very serious environmental problem that continues to be faced by the government and society. The waste produced every year increases along with the increase in population. Making compost from household organic waste is one solution at the household level to reduce the impact of waste and provide organic fertilizer for plants. However, the main problem is the lack of waste processing and public awareness. As an alternative solution, the use of the Internet of Things (IoT) can be utilized. This research utilizes the NodeMCU ESP8266 and DHT11, MQ4 sensors and incandescent lamps to monitor and control the compost making process. Through integration with the Telegram bot, this system allows users to monitor and manage the process remotely, which in turn contributes to reducing waste, environmental pollution and providing organic fertilizer. In this study, the results obtained during the 15 day compost making process had an average temperature of 40.63, humidity 67%, and methane gas produced was less than 700 ppm. The odor produced during composting smells earthy and fragrant, has a brownish black color, and has a crumbly texture, softens easily, and experiences weight loss. From the characteristics above, it can be interpreted that the compost made has good quality.

KLASIFIKASI IKAN CAKALANG DAN IKAN TONGKOL MENGGUNAKAN XCEPTION DAN MOBILENET

2025-03-22T03:58:32+08:00

This study compares the performance of two deep learning architectures, Xception and MobileNet, for classifying skipjack and mackerel tuna, with a focus on accuracy and computational efficiency. MobileNet achieved an impressive accuracy of 97%, with precision, recall, and F1-score all at 97%, and demonstrated a faster prediction time of 0.06 seconds, making it well-suited for real-time applications. In contrast, Xception achieved an accuracy of 93%, with a precision of 94%, recall of 93%, and an F1-score of 93%. However, its prediction time was slower at 0.13 seconds, indicating a higher computational complexity. Although Xception delivered substantial accuracy, MobileNet outperformed it in terms of efficiency, suggesting that MobileNet is better suited for applications with limited resources or time constraints. The results indicated that MobileNet's lightweight architecture makes it ideal for mobile or embedded systems. At the same time, Xception's more complex structure may be advantageous for tasks that require higher precision in image processing. This research makes a significant contribution to the development of deep learning-based methods for fish species classification, offering improvements in both accuracy and speed.

PERBAIKAN KESALAHAN KATA MENGGUNAKAN KOMBINASI JARO-WINKLER & JACCARD SIMILARITY

2025-03-22T03:58:32+08:00

Word error correction is challenging due to the variety of errors. This research proposes a combination of two similarity algorithms to improve accuracy. The objective is to evaluate how each algorithm responds to different types of spelling errors and to assess the effectiveness of their combined performance. Jaro-Winkler determines initial similarity by assigning more weight to word prefixes, effectively addressing errors due to transposition and character omission. This algorithm excels in scenarios where the beginning of the word is critical to identifying the correct candidate. In contrast, Jaccard similarity filters candidates based on character set similarity, which helps assess the overall composition similarity of the word but does not consider character order. The test results show that Jaro-Winkler is more dominant in providing relevant correction candidates, with higher accuracy in the 1-best (68.94%) and 5-best (90.78%) scenarios compared to Jaccard (55.25% and 78.42%). This performance difference suggests that Jaro-Winkler is more suitable for the initial screening of candidates. The combination of the two algorithms proved to be more effective in handling different types of word errors than when used separately, resulting in a more robust overall correction mechanism.

SISTEM INFORMASI MONITORING PEMBUATAN SERAGAM PADA YAYASAN AL-FAJAR MATARAM

2025-03-22T03:58:32+08:00

The Al-Fajar Mataram Foundation, an integrated Islamic school that has levels from Kindergarten, Elementary, and Middle School, is facing problems in the process of loading student uniform data, which is still done manually. This process often causes delays, uncertainty, errors, and a lack of transparency for schools and parents regarding the status of uniform production. To overcome this, it is proposed to develop a "Web-Based Uniform Manufacturing Process Monitoring System" using the Prototype method. This method was chosen because it allows users to directly see and test the system from the early stages of development. This provides an opportunity for users to provide suggestions and input directly, which can then be used by developers to improve system features that they feel are lacking, bringing them into line with what is needed. With this system, data regarding the uniform-making process can be managed more easily, making it easier to send data to tailors and allowing parents to monitor the status of their child's uniform-making directly. The results of testing using the Mean Opinion Score indicated a high level of user acceptance, with a User Acceptance Test score of 87.8%. This suggests that the system is highly beneficial for users.

SISTEM INFORMASI PERPUSTAKAAN BERBASIS WEB DI DINAS PERPUSTAKAAN DAN KEARSIPAN KABUPATEN LOMBOK TIMUR DENGAN METODE RAPID APPLICATION DEVELOPMENT (RAD)

2025-03-22T03:58:32+08:00

Libraries are essential tools for supporting education and learning activities. However, libraries in some areas still use manual systems to manage book data and other services. East Lombok Regency is one such area that requires an updated library information system to enhance the efficiency and effectiveness of its services. Observations at the East Lombok Regency Library and Archives Office revealed that library services are still conducted manually, with librarians using notebooks to record book borrowings. This manual system poses challenges in managing borrowed and returned books, especially as the East Lombok Library and Archives Office permit schools nationwide to borrow books. To address these issues, researchers employed the Rapid Application Development (RAD) method to design the information system. This method was chosen for its ability to shorten development time compared to traditional methods. The newly developed library information system aims to assist schools facing a shortage of books, particularly in remote village areas. The application of RAD successfully increased development efficiency and improved the system's effectiveness in meeting the library's operational needs. Furthermore, the system reduced dependence on manual processes, enhanced data accessibility, and simplified library data management. These improvements enable more optimal library services for the residents of East Lombok. This success is supported by the results of a questionnaire, with 80% of respondents agreeing that the system effectively meets their needs.

PERANCANGAN UI/UX PENGUBAH TINGGI NADA PADA SISTEM KARAOKE BERBASIS WEBSITE

2025-03-22T03:58:33+08:00

Karaoke adalah hiburan dimana pengguna menyanyikan lagu dengan musik pengiringnya. Permasalahan yang timbul saat berkaraoke adalah suara fals karena ketidaksesuaian antara musik dan suara pengguna. Penelitian ini bertujuan untuk merancang UI/UX sistem karaoke berbasis website yang dapat menyesuaikan tinggi nada dengan suara pengguna. Metode penelitian yang digunakan adalah design thinking, yang mencakup tahap empathize, define, ideate, prototype, dan testing. Metode ini dipilih karena berfokus pada pengguna dan menciptakan solusi inovatif. Pengujian sistem dilakukan menggunakan System Usability Scale (SUS) untuk mengukur kemudahan penggunaan dan kepuasan pengguna terhadap antarmuka yang dirancang dimana penelitian ini melakukan pengujian pada pelajar dan pekerja yang gemar berkaraoke. Hasil penelitian ini adalah tampilan UI/UX sistem karaoke berbasis web dengan fitur pengubah tinggi nada yang mendapatkan skor SUS 80,17 dengan arti fitur pengubah tinggi nada pada sistem ini bersifat acceptable dan excellent .

PENGEMBANGAN SISTEM PAKAR DENGAN METODE NAÏVE BAYES UNTUK DIAGNOSA PENYAKIT BURUNG PUYUH

2025-03-22T03:58:33+08:00

The increasing need for quail farmers to identify diseases quickly and accurately, considering that many farmers do not have in-depth knowledge about the symptoms of diseases that may occur and the treatments that must be administered once the quails are infected. The lack of veterinarians also causes farmers to be anxious about handling diseases that affect quails. This research aims to develop an expert system that diagnoses quail diseases using the Naïve Bayes method. The methods applied in this study include collecting data on quail disease symptoms, processing data to transform categorical values into numerical ones, and implementing the Naive Bayes algorithm by dividing the dataset into training and testing data. The research results show that the developed model achieved an accuracy of 82.75% in diagnosing quail diseases. This accuracy is quite competitive compared to previous studies that used similar methods for other livestock with accuracy levels ranging from 60% to 90%. The system's performance evaluation using a confusion matrix and classification report indicates that the model can classify most cases correctly, although there are some prediction errors in certain classes. This shows that the effectiveness of the expert system in diagnosing quail diseases using the Naive Bayes method can provide a solution for farmers to recognize and address diseases earlier.

SISTEM INFORMASI MANAJEMEN AKADEMIK DAN KEUANGAN YAYASAN AN-NAWAWI AL-HAKIIMIY MENGGUNAKAN METODE PROTOTYPING

2025-03-22T03:58:33+08:00

Effective management is a crucial aspect in the operational dynamics of educational institutions. This research aims to develop a Website-Based Academic and Financial Management Information System for the An-Nawawi Al-Hakiimiy Foundation using the prototyping method. The system, developed using the Laravel framework, is designed to optimize various academic and financial management processes, including administration, student and teaching staff data management, attendance tracking, student evaluation and assessment, charity (infaq) recording, and financial management. Through the prototyping method, the system was developed incrementally by involving users in both the design and testing processes. The User Acceptance Testing (UAT) results demonstrated an average assessment score of 95.3%, indicating that the system is highly effective and ready for implementation. This research is expected to significantly enhance the efficiency and effectiveness of the foundation's operational management through the utilization of information technology.

KLUSTERING TOPIK PADA KOLOM KOMENTAR INSTAGRAM TENTANG KABINET MERAH PUTIH MENGGUNAKAN METODE K-MEANS

2025-03-22T03:58:33+08:00

This research attempts to determine the primary themes that Indonesians talked on President Prabowo Subianto's "Merah Putih" cabinet by using clustering analysis of Instagram comments. Using crawling data from the Instagram platform with the hashtag #KabinetMerahPutih, comments were gathered using the K-Means Clustering approach. Prior to the data being analyzed to create five clusters, the cleaning and pre-processing procedure, which included tokenization with IndoBERT and dimensionality reduction using Principal Component Analysis (PCA), was able to greatly improve the clustering quality, with the Silhouette Coefficient value rising from 0.010 to 0.200. Out of 23.780 initial data, 9.320 clean data were processed for this investigation. The findings demonstrate that the K-Means algorithm can group comments according to pertinent themes and offer profound understanding of support more responsive public policy analysis.

IMPLEMENTASI OWASP TOP 10 DALAM PENGUJIAN PENETRASI WEBSITE : MENGIDENTIFIKASI CELAH KEAMANAN DALAM SISTEM PENGELOLAAN VOTING INDONESIA

2025-03-22T03:58:33+08:00

The rapid advancement of information technology has had a major influence in every aspect of life, including in government operations. the availability of platforms such as websites can be a medium for disseminating information transparently, especially in Indonesia's democratic process, namely elections. However, this digital convenience also presents cybersecurity challenges. therefore this research focuses on identifying security gaps in the voting management system in Indonesia by conducting penetration testing based on the OWASP Top 10 2021. in conducting penetration testing, it focuses on 10 subdomains on the targeted voting management website. This research process starts from the process of scanning and testing security using various tools such as subfinder, dirsearch, nuclei, ex-param and JSRecon. thus getting the analysis results that of the 10 targets 9 of them have vulnerabilities related to the OWASP Top 10 categories, such as A01-Broken Access Control, A03-Injection, A05-Security Misconfiguration, and A06-Vulnerable and Outdated Components. Broken Access Control is the most commonly found gap, identified in 6 subdomains. this research aims to improve the security of voting management systems in Indonesia while contributing to the sustainability of a more secure digital democracy in Indonesia.

SISTEM INFORMASI KOPERASI SIMPAN PINJAM PADA KSP MITRA MANDIRI BERBASIS WEBSITE

2025-03-22T03:58:33+08:00

Koperasi simpan pinjam merupakan organisasi bisnis yang dimiliki dan dioperasikan oleh anggota untuk kepentingan Bersama. Selain itu koperasi simpan pinjam juga merupakan jenis koperasi yang menyediakan layanan simpan dan pinjam untuk anggotanya. Dalam koperasi ini, anggota dapat menyimpan uang mereka dan mendapatkan bunga dari simpanan tersebut, serta meminjam uang dengan bunga yang lebih rendah dibandingkan lembaga keuangan lainnya. Tujuan utama koperasi simpan pinjam adalah membantu anggota yang membutuhkan dana dengan memberikan akses pinjaman yang lebih mudah dan dengan syarat yang lebih ringan, serta meningkatkan kesejahteraan anggota secara finansial. KSP Mitra Mandiri adalah salah satu koperasi yang digunakan oleh Masyarakat sebagai tempat meminjam modal.Berdasarkan informasi yang diperoleh dari Koperasi Simpan Pinjam KSP Mitra Mandiri bahwa dalam proses rekapan data koperasi simpan pinjam masih dikelola dengan menggunakan aplikasi Microsoft excel. Sehingga tujuan merancang sistem informasi ini adalah mempermudah pegawai dalam menginput data dan mempercepat layanan kepada anggota koperasi. Di dalam perancangannya, sistem ini akan menggunakan bahasa pemrograman PHP dengan database MySQL. Pengujian pada aplikasi ini menggunakan black boxtesting dan System Usability Scale (SUS). Hasilnya aplikasi dapat berjalan dengan baik sesuai dengan fungsionalitas masing – masing dan sesuai dengan user story yang diinginkan. Pengujian skalabilitas menggunakan metode System Usability Scale (SUS) dengan hasil akhir sebesar 73,75%, adjective scale Good dan grade scale C, menandakan bahwa sistem memiliki kualitas yang baik.

OPTIMALISASI LAYANAN SISTEM INFORMASI MAHASISWA DENGAN INTEGRASI TELEGRAM : CHATBOT RETRIEVAL-AUGMENTED-GENERATION BERBASIS LARGE LANGUAGE MODEL

2025-03-22T03:58:33+08:00

Kemajuan teknologi telah memberikan dampak yang cukup signifikan dalam berbagai bidang, termasuk salah satunya Pendidikan. Dalam aspek Pendidikan permasalahan yang dihadapi adalah keterbatasan akses mahasiswa terhadap informasi akademik secara cepat dan efisien. Untuk mengatasi hal ini, penelitian ini bertujuan mengembangkan chatbot berbasis Telegram yang mampu memberikan respons informatif, akurat, dan ringkas terhadap pertanyaan pengguna terkait akademik di program studi Teknik Informatika. Chatbot ini memanfaatkan metode Retrieval-Augmented-Generation (RAG) untuk memproses informasi dari dokumen teks secara efisien. Metode RAG digunakan untuk menemukan jawaban yang relevan dari dokumen berdasarkan pertanyaan pengguna, sementara Large Language Model memahami konteks pertanyaan dan menghasilkan jawaban yang sesuai. Penelitian ini menggunakan pendekatan Research and Development (R&D) dengan tahapan meliputi survei questioner kebutuhan mahasiswa, preprocessing data, Pembangunan indeks pencarian berbasis vektor, konfigurasi model LLM, serta integrasi chatbot dengan Telegram. Hasil pengujian menunjukkan bahwa chatbot mampu memberikan jawaban dengan akurasi tinggi dan waktu respons rata-rata 60 detik untuk pertanyaan sederhana hingga kompleks, sehingga chatbot berbasis RAG cukup efektif meningkatkan aksesibilitas informasi secara real-time. Pengembangan lebih lanjut dapat difokuskan pada peningkatan pemahaman terhadap beragam pertanyaan dan personalisasi respons.

PENDEKATAN SENTIMEN BERBASIS ASPEK PADA ULASAN SIRKUIT MANDALIKA MENGGUNAKAN CNN DAN REPRESENTASI FASTTEXT

2025-03-22T03:58:34+08:00

Reviews are texts that contain an assessment or comment on something and can be used to provide more in-depth information. This research aims to analyze community reviews of the Mandalika Circuit using the aspect-based sentiment analysis technique CNN method. The CNN model is trained using two types of word embedding, namely Keras and FastText, and supported by the Multilabel Stratified K-Fold Cross Validation method to ensure an even distribution of data on each label and produce a stable accuracy evaluation. The results show that CNN with FastText word embedding has a higher average accuracy than CNN with Keras word embedding for both aspect and sentiment classification tasks. However, the model had difficulty in classifying the positive class in the sentiment label, which was due to the smaller amount of review data with positive sentiment than neutral and negative. Therefore, for future research, it is recommended to use data augmentation techniques on the imbalanced classes to improve the accuracy of the model.

THREAT MODELING MENGGUNAKAN PENDEKATAN STRIDE DAN DREAD UNTUK MENGETAHUI RISIKO DAN MITIGASI KEAMANAN PADA SISTEM LAYANAN PENDIDIKAN

2025-03-22T03:58:34+08:00

Information system security is increasingly crucial with the rise of cyber threats. This study identifies and evaluates security risks in education service systems using STRIDE and DREAD-based Threat Modeling. STRIDE identifies threats such as spoofing, tampering, repudiation, information disclosure, denial of service, and elevation of privilege, while DREAD assesses risk based on potential damage, ease of exploitation, affected users, and likelihood of detection. The analysis showed that information disclosure and elevation of privilege were the highest risks, mainly due to the permissive CORS configuration. Testing using Burp Suite revealed high-level vulnerabilities allowing unauthorized access and data leakage. To address this, mitigations in the form of CORS policy validation, HTTP method restrictions, data encryption, and role-based authentication were implemented. Simulation results after mitigation showed a significant reduction in security issues, such as critical issues dropping from 6 to 1. This research confirms STRIDE and DREAD are effective in identifying and evaluating security risks, providing a strong basis for designing mitigation strategies to maintain educational service security.

PENGEMBANGAN SISTEM INFORMASI PENYALURAN BANTUAN BERBASIS WEBSITE STUDI KASUS BALAI PENYULUHAN PERTANIAN KECAMATAN KEMPO

2025-03-22T03:58:34+08:00

The agricultural sector is a key pillar of Indonesia's economy, including in West Nusa Tenggara (NTB) Province. According to 2023 census data from the Central Statistics Agency (BPS), 768,765 farmers are engaged in Individual Agricultural Enterprises (UTP), with 46,910 from Dompu Regency, linked to the Agricultural Extension Center (BPP). BPP Kempo District faces inefficiencies in aid distribution due to manual processes using books and paper, leading to data recording errors. To address this, a web-based aid distribution information system was developed, providing aid registration and announcement features to facilitate data management and communication. This study aims to enhance aid distribution efficiency by digitizing manual processes. The Prototyping method was applied to allow early user feedback, ensuring improvements before the final system deployment. This approach helps minimize errors and aligns the system with user needs. The results, based on black-box testing and User Acceptance Testing (UAT), confirm the system's effectiveness. Black-box testing with end users verified that all features met expectations, while UAT showed an 87.95% satisfaction rate, categorized as "very good." Thus, this system improves the effectiveness of aid distribution in Kempo District.