Garuda - Garba Rujukan Digital

Penerapan Metode Naïve Bayes untuk Analisis Sentimen pada Ulasan Pengguna Aplikasi ChatGPT di Google Play Store Hermawan, Tri Ramadhani Putra; Dzikrillah, Akhmad Rizal
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5400

ChatGPT is a chatbot application developed by OpenAI. It has attracted a large number of users in a short period of time. User comments are categorized into positive and negative, indicating their sentiments on using this app. Although ChatGPT provides convenience from its various features, it also has its downside if misused. Some people think that people will depend on the information provided by this chatbot and reduce the desire to find out the information themselves, because the information from ChatGPT still uses the old generation model. From this concern, a deeper research on sentiment analysis of people who have used the ChatGPT application is made. It is hoped that this research will be able to collect data on public responses to ChatGPT, both pros and cons. Research data will be taken from reviews of ChatGPT application users in the Play Store. Google Collaboratory with Google Play Scraper will be used during the data collection process. The data that has been obtained will go through a preprocessing stage to be cleaned. After the data is successfully cleaned, the data will go through the process of labeling positive and negative data, and will be classified through the Naïve Bayes method. The study results show that the application of the Naïve Bayes method is able to classify user sentiment using Confusion Matrix with a percentage accuracy value of 94.05%, a percentage precision value of 95% for positive and 81.25% for negative. Then the percentage of recall value for positive is 98.84%, and for negative is 48%.

IMPELEMENTASI WIRELESS SEBAGAI MEDIA KOMUNIKASI PADA SOFTWARE KENDALI MANIPULATOR MOBILE MULTI LENGAN Irwansyah, Irwansyah; Dzikrillah, Akhmad Rizal; Aditya, Muhammad Rifky; Al-Fadillah, Syafira Nadia; Makhfuz, Maulana Muhammad
Infotech: Journal of Technology Information Vol 10, No 1 (2024): JUNI
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v10i1.242

Robots or manual manipulators are a type of robot whose movements are completely controlled by humans. In certain cases, errors in the robot's work area endanger humans, so manual control of the robot at close range is not recommended. Robots in certain cases need to be controlled at medium or long distances. The use of cables as a medium for transmitting control signals over medium/long distances has weaknesses in controlling mobile robots or robots whose positions dynamically move from place to place. If controlled using a cable, a manual mobile robot requires a long stretched cable so that it cannot hinder the speed of the robot's movement so it is more efficient if controlled wirelessly. Bluetooth technology can be used as a medium for wireless transmission of medium distance control signals. The aim of this research is to design wireless-based multi-arm mobile device control software. Research methods start from mechanical, electrical, user interface and robot algorithm design. The robot designed is a manual-armed robot whose movements can be controlled by a user interface device that is connected wirelessly using Bluetooth. After getting a mature design, research was carried out on making robots and interface devices. The first stage of testing was carried out to test the robot's electricity, mechanics, user interface connection with the robot, and algorithm control. If the mechanical-electrical performance is successful and the user interface is connected, and the algorithm is appropriate, then the robot is declared complete. If the electrical, mechanical and control algorithm performance does not meet expectations, then the construction of the robot will be repeated on parts of the performance that do not function as expected. By utilizing Bluetooth media on the PS2 game pad, a forklift mechanism, programming servo angles on the claws, and a holonomic wheel system, a multi-arm manipulator can be created that has 4 degrees of freedom to move objects, namely moving forward and backward, shifting right and left, lifting. - lower the object, turn left and right. The multi-arm manipulator can be controlled wirelessly using Bluetooth technology. ABSTRAKRobot atau Manipulator manual merupakan jenis robot yang pergerakannya dikendalikan oleh manusia sepenuhnya. Pada beberapa kasus tertentu, misal pada areakerja robot yang membahayakan manusia, maka pengendalian robot manual pada jarak dekat tidak disarankan. Robot pada kasus tertentu perlu dikendalikan pada jarak menengah atau jarak jauh. Penggunaan kabel sebagai media transmisi sinyal kendali jarak menengah/jauh memiliki kelemahan pada kendali robot mobile atau robot yang posisinya dinamis berpindah-pindah tempat. Jika dikendalikan menggunakan kabel maka robot mobile manual membutuhkan kabel yang terulur panjang agar tidak dapat menghambat laju gerak robot sehingga lebih efisien jika dikendalikan secara wireless. Teknologi bluetooth dapat digunakan sebagai media transmisi sinyal kendali jarak menegah secara wireless. Tujuan dari penelitian ini adalah merancang bangun software kendali perangkat mobile multi lengan berbasis wireless. Metode penelitian dimulai dari perancangan mekanik,elektrik, interface pengguna, serta algorithma robot. Robot yang dirancang adalah robot berlengan manual yang pergerakannya daoat dikendalikan oleh perangkat antarmuka pengguna yang terhubung secara wireless menggunakan bluetooth. Setelah mendapatkan perancangan yang matang, penelitian dilakukan dengan pembuatan robot dan perangkat antarmuka. Pengujian tahap pertama dilakukan untuk menguji elektrik, mekanik robot, koneksi interface pengguna dengan robot, serta algorithma kendali. Jika kinerja mekanik-elektrik berhasil serta interface pengguna terkoneksi, dan algoritma sesuai, maka robot dinyatakan selesai. Jika kinerja elektrik, mekanik, dan algorithma kendali belum sesuai ekspektasi,maka pembuatan robot akan diulangi di bagian kinerja yang belum berfungsi sesuai ekspektasi. dengan memanfaatkan media bluetooth pada game pad PS2, mekanisme forklift, pemrograman sudut servo pada capit, serta sistem roda holonomic, maka dapat dibuat manipulator multi lengan yang memiliki 4 derajat kebebasan untuk memindahkan objek yaitu bergerak maju-mundur, geser kanan-kiri, mengangkat-menurunkan objek, berbelok ke kanan-kiri. Manipulator multi lengan tersebut dapat dikendalikan secara wireless menggunakan teknologi bluetooth.

Analisis Sentimen dan Topik Perbincangan Netizen Indonesia Terkait Pengurangan Subsidi BBM Mulia, Adi; Dzikrillah, Akhmad Rizal
Jurnal Linguistik Komputasional Vol 7 No 1 (2024): Vol. 7, NO. 1
Publisher : Indonesia Association of Computational Linguistics (INACL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jlk.v7i1.142

Abstract- This research was conducted with the aim that is based on problems that arise in society, namely the increase in fuel prices. The sentiment classification method applied by researchers is to use a lexicon corpus dictionary that takes into account positive and negative sentiment values. The researcher then compares the sentiment between before and after the fuel price increase policy. Furthermore, the researcher applied Latent Dirichlet Allocation or (LDA) topic modeling to find out whether the discussion of the fuel price increase became the main topic when the fuel rose. The results of this study show that after announcing the fuel price increase in September 2022, the percentage of negative tweets directed at President Jokowi has increased when compared to before announcing the fuel price increase. The percentage of positive tweets directed at President Jokowi decreased when compared to before raising fuel prices. In the month when President Jokowi announced the fuel price increase policy, namely in September 2022, the topic of conversation related to the fuel price increase policy was the most popular topic of conversation in tweets directed at President Jokowi. 33.8% of tweets that discussed the fuel price increase were negative tweets with the most popular topics of discussion for netizens with negative sentiments were topics related to criticism of the Jokowi administration.

Optimizing Consistency and Efficiency of Simakip’s Frontend Architecture Through Implementation of Atomic Design Method Nova, Sabrina Qodri; Dzikrillah, Akhmad Rizal
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6607

The Research and Community Service Performance Management System (SIMAKIP) is a centralized website that facilitates UHAMKA academicians to report research and community service activities periodically, by submitting valid research and scientific publications to the ristekdikti website for performance assessment. The problem is that centralized information systems have a wide range of feature complexity, making it important to ensure design consistency and efficiency of interface component development. To address the problem, the implementation of an atomic design approach is used as an innovative method that utilizes reusable modular components in five stages namely atom, molecule, organism, template and page for structured and integrated component development across the application. The purpose of this research is to improve the frontend architecture of SIMAKIP UHAMKA to optimize the performance of the development team and SIMAKIP as a whole, which will contribute to the advancement of research and community service within the academic community. Based on User Acceptance Test (UAT) testing by conducting 10 test cases to 10 participants, it was found that the overall SIMAKIP frontend architecture achieved a percentage of conformity of 95.96% in the Very Good category. These results prove the success of the atomic design approach to the consistency and efficiency of UHAMKA SIMAKIP and have the potential to become a model for other institutions as well as a reference for research in the field of other academic information systems.

Komparasi MobileNETV2 dengan Kustomisasi Transfer Learning dan Hyperparameter untuk Identifikasi Tumor Otak Somoal, Muhammad Gabriel; Dzikrillah, Akhmad Rizal
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 12 No 1: Februari 2025
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2025129582

Tumor otak disebabkan dengan pertumbuhan sel otak yang abnormal pada jaringan otak yang menyebabkan kematian bagi pria dan wanita. Identifikasi tumor otak umumnya dilakukan dengan metode biopsi oleh dokter selama 10 hingga 15 hari. Namun, pendekatan modern diperlukan untuk menekan waktu dalam identifikasi tumor otak dengan teknologi deep learning. Dalam penelitian ini, menggunakan 4 kategori tumor otak yaitu glioma, meningioma, notumor, dan pituitary dengan akumulasi citra data sebanyak 20.000 data dan pembagian data meliputi 75% untuk train data, 15% untuk validation data, dan 10% untuk testing data. Penelitian ini bertujuan untuk membandingkan performa dari Adam dan Stochastic Gradient Descent Optimizer, dan model arsitektur transfer learning MobileNetV2 dan MobileNetV2 dalam identifikasi tumor otak. Penelitian ini menggunakan metode komparatif dengan metode evaluasi menggunakan confusion matrix. Comparative analysis dilakukan dengan membandingkan 4 skenario meliputi skenario 1 yaitu menggunakan Adam optimizer dan transfer learning, skenario 2 yaitu menggunakan SGD optimizer dan transfer learning, skenario 3 yaitu menggunakan Adam optimizer dan tanpa transfer learning, serta skenario 4 yaitu menggunakan SGD optimizer dan tanpa transfer learning. Hasil penelitian menunjukkan bahwa skenario 1 dengan penggunaan Adam optimizer dan model transfer learning MobileNetV2 memperoleh accuracy sebesar 98%, precision sebesar 98%, recall sebesar 97,75%, dan f1-score sebesar 97,75% yang merupakan hasil model terbaik, Temuan ini mengindikasikan bahwa peran transfer learning sangat berpengaruh baik pada performa model dan diharapkan dapat memberikan wawasan lebih mendalam terkait model arsitektur yang paling akurat untuk identifikasi tumor otak serta menawarkan fondasi untuk pengembangan aplikasi berbasis Magnetic Resonance Imaging dalam citra medis. Abstract Brain tumors are caused by the abnormal growth of brain cells in brain tissue, leading to death for both men and women. Typically, brain tumor identification is performed through a biopsy by doctors, taking 10 to 15 days. However, a modern approach is needed to reduce the time for brain tumor identification using deep learning technology. This study uses four categories of brain tumors: glioma, meningioma, no tumor, and pituitary tumor, with a dataset of 20,000 images. The data is divided into 75% for training, 15% for validation, and 10% for testing. The purpose of this study is to compare the performance of the Adam and Stochastic Gradient Descent (SGD) optimizers, as well as the MobileNetV2 and MobileNetV2 transfer learning architecture models in brain tumor identification. A comparative method is used, with evaluation through a confusion matrix. The analysis compares four scenarios: Scenario 1 using the Adam optimizer and transfer learning, Scenario 2 using the SGD optimizer and transfer learning, Scenario 3 using the Adam optimizer with no transfer learning, and Scenario 4 using the SGD optimizer with no transfer learning. The results show that Scenario 1, using the Adam optimizer and MobileNetV2 transfer learning, achieved the highest performance with 98% accuracy, 98% precision, 97.75% recall, and 97.75% F1-score. This finding highlights the significant impact of transfer learning on model performance, providing valuable insights into the most accurate architecture for brain tumor identification, and offers a foundation for developing Magnetic Resonance Imaging-based medical image applications.

DATABASE-BASED GUI SYSTEM TO INCREASE THE EFFECTIVENESS OF STUDENT DATA MANAGEMENT IN THE FKIP UHAMKA DORMITORY AMURU, ISMAT; Dzikrillah, Akhmad Rizal
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024 - SENIKO
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.1981

Data management in the digital era is crucial in various institutions. One of these institutions is the dormitory or student residence, where it's important to track the progress achieved by the residents. However, data management at the FKIP UHAMKA Dormitory still faces several challenges, particularly regarding the loss of previous evaluation data, which is essential for the management. Data loss is a significant issue in the data management process for the relevant institution. Hence, there is a need for innovation in designing a database system that is user-friendly for data management in the digital era. This research aims to develop a GUI-based database system to efficiently manage student data at the FKIP UHAMKA Dormitory. The research adopts the waterfall development method, which involves stages such as requirements analysis, design, coding, and testing. Data is obtained through observation, interviews, and literature studies. The results of the research indicate that the GUI application based on the Dormitory FKIP UHAMKA Database has a good level of usability, with a System Usability Scale (SUS) score of 73.654. This suggests that users find the application easy to use and efficient in meeting their needs related to dormitory management. In addition to the SUS evaluation, this research stands out for developing a more comprehensive GUI system with significant additional features.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search