Journal of Advances in Computational Intelligence and Information Systems

Hotspot Design And Construction of Server Hotspot Networks Mikrotik Using the One User Two Client Method In The Teacher's Room At SMK Negeri 1 Sarudik

Adila Mawadda Meuraxa — 2025-02-27

Internet technology has become a necessary tool in everyone's daily life in this digital era. The need for fast and easily accessible communication media has been fulfilled through internet technology. The Internet network has developed into a crucial factor in various aspects of human life. For example, in the fields of transportation, government, education, and others. In the field of education, internet technology is very important for finding relevant and useful information from various sources around the world. Teachers in a school can access a wide variety of information on various topics. Therefore, every school should have provided hotspot facilities that can be accessed on every laptop and smartphone they have so that every teacher who is at the school or who is waiting for their teaching schedule in the teacher's room can get internet service to support the learning process so that more efficient, and with this internet facility and to implement the hotspot network. Due to the large number of bottlenecks on networks that are used simultaneously, here the author created a hotspot using a Mikrotik router as the main server of the hotspot network which is divided so that everyone can access it without any problems.

Sentiment Analysis Of The Indrive Application Reviews On Google Play Store Using The Naive Bayes Method

Ramadhan Pratama — 2025-02-27

The development of application-based technology on Android smartphones has transformed daily activities, including the transportation sector. One popular online transportation application is inDrive, offering features such as fare negotiation and driver selection criteria. With over 100 million downloads and 8 million reviews on Google Play Store, sentiment analysis of user reviews is crucial for evaluating user satisfaction and providing insights for application developers. This study aims to analyze user sentiment on inDrive app reviews from the Google Play Store using the Naïve Bayes algorithm. The research adopts a quantitative approach with a dataset of 1,000 reviews collected through web scraping using Google Colab. The methodology includes sentiment labeling (positive and negative), data preprocessing (case folding, tokenizing, stopword removal, and stemming), weighting using Term Frequency-Inverse Document Frequency (TF-IDF), classification with the Naïve Bayes algorithm, model evaluation using a confusion matrix, and data visualization through word clouds. The results show that most user reviews are positive. The Naïve Bayes algorithm demonstrated good performance, achieving an accuracy of 80%, precision of 84%, and recall of 77%. Data visualization revealed frequently used words in positive reviews such as "excellent," "great," and "helpful," while negative reviews highlighted words like "please" and "driver." This study contributes to leveraging sentiment analysis to evaluate online transportation applications. Future research is recommended to explore alternative algorithms, such as K-Nearest Neighbor (KNN) or Support Vector Machine (SVM), and expand datasets with larger and more diverse data sources. These approaches are expected to enhance sentiment analysis model performance and provide deeper insights into user sentiment patterns..

Using Neural Networks to Predict Diabetes Diagnosis through Backpropagation Algorithm

Abwabul Jinan — 2025-02-27

Diabetes is a chronic disease caused by the body's inability to produce or effectively use insulin. This condition can lead to various serious complications. The backpropagation algorithm is one of the models found in Artificial Neural Networks (ANN) that employs supervised learning. This algorithm is often used to solve complex problems due to its training through learning methods. This study aims to develop an ANN model using the backpropagation algorithm to predict diabetes based on existing symptoms. By utilizing patients' medical records, this model is expected to provide accurate predictions regarding diabetes diagnosis