Recursive Journal of Informatics

Application Design for the Deaf Users of Trans Jogja Based on Android

2024-03-31T18:54:03+07:00

Abstract This study proposes the design and development of an Android application tailored specifically for the deaf users of the Trans Jogja public transportation system. With the aim of enhancing accessibility and usability for this marginalized user group, the application integrates features that cater to their unique communication needs and challenges.

Purpose: Universitas Nahdlatul Ulama Yogyakarta has a Disability Services Unit or ULD called GESI. This unit accommodates the accessibility needs of deaf students. Deaf students usually use Trans Jogja as a means of transportation to campus. An obstacle that students often face is missing the location of their destination bus stop. This happens because students are too busy playing with their cell phones, causing a loss of focus. Therefore, tools are needed as a reminder of the location of the destination bus stop. This research aims to design a tool application for deaf students using Android-based Trans Jogja public transportation.

Methods/Study design/approach: This research methods uses a prototype which includes communication, quick plan and design modeling, construction of prototype, and development delivery feedback.

Result/Findings: The results of this research are in the form of a prototype that has several features, namely searching for starting and destination stops, text to voice, word dictionary, volume settings, and distance settings.

Novelty/Originality/Value: The design of an application to assist deaf people in using Trans Jogja based on Android is used for students with hearing impairments, especially for Trans Jogja public transportation.

Fruit Freshness Detection Using Android-Based Transfer Learning MobileNetV2

2024-03-31T18:54:04+07:00

Abstract. Fruit is an important part of the source of food nutrition in humans. Fruit freshness is one of the most important factors in selecting fruit that is suitable for consumption. Fruit freshness is also an important factor in determining the price of fruit in the market. So it is very necessary to detect fruit freshness which can be done by machine. Take apples, bananas, and oranges as samples. The machine learning algorithm used in this study uses MobileNetV2 with transfer learning techniques. MobileNetV2 introduces many new ideas aimed at reducing the number of parameters to make it more efficient to run on mobile devices and achieve high classification accuracy. Transfer learning is used so that data does not need training from the start, so it only takes several networks from MobileNetV2 that have previously been trained and then retrained with a different purpose to improve accuracy results. Then the models that have been created are inserted into the application using Android Studio. Software testing is done through black box testing.

Purpose: The purpose of this research is to design a machine-learning model to detect fruit freshness and then apply it to application Android smartphones.

Methods/Study design/approach: The algorithm used in this study uses MobileNetV2 with transfer learning techniques. Models that have been created are inserted into the application using Android Studio.

Result/Findings: The training results using MobileNetV2 transfer learning obtained an accuracy of 99.62% and the loss results obtained were 0.34%. The results of the application after testing using the black box testing method required improvements to the application and the machine learning model so that it can run optimally.

Novelty/Originality/Value: Machine learning models that have been created using transfer learning MobileNetV2 are applied to Android applications so that they can be used by the public.

Application of C4.5 Algorithm Using Synthetic Minority Oversampling Technique (SMOTE) and Particle Swarm Optimization (PSO) for Diabetes Prediction

2024-03-31T18:54:05+07:00

Abstract. Diabetes is the fourth or fifth leading cause of death in most developed countries and an epidemic in many developing countries. Early detection can be a preventive measure that uses a set of existing data to be processed through data mining with a classification process.

Purpose: Investigate the efficacy of integrating the C4.5 algorithm with Synthetic Minority Oversampling Technique (SMOTE) and Particle Swarm Optimization (PSO) for improving the accuracy of diabetes prediction models. By employing SMOTE, the study aims to address the class imbalance issue inherent in diabetes datasets, which often contain significantly fewer instances of positive cases (diabetes) than negative cases (non-diabetes). Furthermore, by incorporating PSO, the research seeks to optimize the decision tree construction process within the C4.5 algorithm, enhancing its ability to discern complex patterns and relationships within the data.

Methods/Study design/approach: This study proposes the use of the C4.5 classification algorithm by applying the synthetic minority oversampling technique (SMOTE) and particle swarm optimization (PSO) to overcome problems in the diabetes dataset, namely the Pima Indian Diabetes Database (PIDD).

Result/Findings: From the research results, the accuracy obtained in applying the C4.5 algorithm without the preprocessing process is 75.97%, while the results of the SMOTE application of the C4.5 algorithm are 80%. Meanwhile, applying the C4.5 algorithm using SMOTE and PSO produces the highest accuracy, with 82.5%. This indicates an increase of 6.53% from the classification results using the C4.5 algorithm.

Novelty/Originality/Value: This research contributes novelty by proposing a hybrid approach that combines the C4.5 decision tree algorithm with two advanced techniques, Synthetic Minority Oversampling Technique (SMOTE) and Particle Swarm Optimization (PSO), for the prediction of diabetes. While previous studies have explored the application of machine learning algorithms for diabetes prediction, few have examined the synergistic effects of integrating SMOTE and PSO with the C4.5 algorithm specifically.

Hyperparameter Tuning of Long Short-Term Memory Model for Clickbait Classification in News Headlines

2024-03-31T18:54:06+07:00

Abstract. The information available on the internet nowadays is diverse and moves very quickly. Information is becoming easier to obtain by the general public with the numerous online media outlets, including news portals that provide up-to-date information insights. Various news portals earn revenue from advertising using pay-per-click methods that encourage article writers to use clickbait techniques to attract visitors. However, the negative effects of clickbait include a decrease in journalism quality and the spread of hoaxes. This problem can be prevented by using text classification to classify clickbait in news titles. One method that can be used for text classification is a neural network. Artificial neural networks use algorithms that can independently adjust input coefficient weights. This makes this algorithm highly effective for modeling non-linear statistical data. The artificial neural network algorithm, especially the Long Short-Term Memory (LSTM), has been widely used in various natural language processing fields with satisfying results, including text classification. To improve the performance of the neural network model, adjustments can be made to the model's hyperparameters. Hyperparameters are parameters that cannot be obtained through data and must be defined before the training process. In this research, the Long Short-Term Memory (LSTM) model was used in clickbait classification in news titles. Sixteen neural network models were trained with different hyperparameter configurations for each model. Hyperparameter tuning was carried out using the random search algorithm. The dataset used was the CLICK-ID dataset published by William & Sari, 2020[1], with a total of 15,000 annotated data. The research results show that the developed LSTM model has a validation accuracy of 0.8030, higher than William & Sari's research, and a validation loss of 0.4876. Using this model, researchers were able to classify clickbait in news titles with fairly good accuracy.

Purpose: The study was to develop and evaluate a LSTM model with hyperparameter tuning for clickbait classification on news headlines. The thesis also aims to compare the performance of simple LSTM and bidirectional LSTM for this task.

Methods: This study uses CLICK-ID dataset and applies different text preprocessing techniques. The dataset later was used to build and train 16 LSTM models with different hyperparameters and evaluates them using validation accuracy and loss. This study uses random search for hyperparameter tuning.

Result: The results of the study show that the best model for clickbait classification on news headlines is a bidirectional LSTM model with one layer, 64 units, 0.2 dropout rate, and 0.001 learning rate. This model achieves a validation accuracy of 0.8030 and a validation loss of 0.4876. The results also show that hyperparameter tuning using random search can improve the performance of the LSTM models by avoiding zero probabilities and finding the optimal values for the hyperparameters.

Novelty: This study compares and analyzes the different preprocessing methods on text and the different configurations of the models to find the best model for clickbait classification on news headlines. The study also uses hyperparameter tuning to tune the model into the best model and finding the optimal values for the hyperparameters.

Comparison of Naive Bayes Classifier and K-Nearest Neighbor Algorithms with Information Gain and Adaptive Boosting for Sentiment Analysis of Spotify App Reviews

2024-03-31T18:54:08+07:00

Abstract. At this time, the development of technology are increase rapidly. One of the issue that appear with advance technology is data volume in the world has increase too. With the large data volumes that exist in the world it can be used to some purpose in many field. Entertainment is one of the field that have many interest from user in this world. Spotify is the example of entertainment apps that provided by Google Play Store to give online music streams to their users. Because that apps is provided by Google Play Store, many reviews of the user about the apps it can be classified to know the positive, negative, or neutral. One way to classified the review of user is make sentiment analysis. In this paper, to classify the review we use naïve Bayes classifier and k-nearest neighbors that will be compared with adding Information gain as feature selection and adaptive boosting as boosting algorithm of each classification algorithm that we used. The result of classification using naïve Bayes classifier with adding Information gain and adaptive boosting is 87.28% and k-nearest neighbor with adding information gain and adaptive boosting can perform accuracy of 80.35%.

Purpose: Knowing the result each of accuracy from the naïve Bayes classifier and k-nearest neighbor algorithm with adding information gain and adaptive boosting that we used and know how to doing the sentiment analysis step by step with the methods that chosen in this study.

Methods/Study design/approach: This study applied data preprocessing, lexicon based labelling with TextBlob, Normalization, Word Vectorization using TF-IDF, and classification with naïve Bayes classifier and k-nearest neighbor, information gain as feature selection, and adaptive boosting as boosting algorithm to boost the accuracy of classification result.

Result/Findings: The accuracy of naïve Bayes classifier with adding information gain and adaptive boosting is 87.28%. Meanwhile, by k-nearest neighbor with adding information gain and adaptive boosting reach the accuracy of 80.35%. This result obtained by using 60.000 dataset with data splitting 80% as data training and 20% as data testing.

Novelty/Originality/Value: Implementing information gain as feature selection and adaptive boosting as boosting algorithm to naïve Bayes classifier is prove that it can be increase the accuracy of classification, but not same when implementing in k-nearest neighbor. So, for the future research can applied another classification algorithm or feature selection to get better result.

Hyperparameter Optimization Using Hyperband in Convolutional Neural Network for Image Classification of Indonesian Snacks

2024-03-31T18:54:09+07:00

Abstract. Indonesia is known for its traditional food both domestically and abroad. Several cakes are included in favorite traditional foods. Of the many types of cakes that exist, it is visually easy to recognize by humans, but computer vision requires special techniques in identifying image objects to types of cakes. Therefore, to recognize objects in the form of images of cakes as one of Indonesian specialties, a deep learning algorithm technique, namely the Convolutional Neural Network (CNN) can be used.

Purpose: This study aims to find out how the Convolutional Neural Network (CNN) works by optimizing the hyperband hyperparameter in the classification process and knowing the accuracy value when hyperband is applied to the optimal hyperparameter selection process for classifying Indonesian snack images.

Methods/Study design/approach: This study optimizes the hyperparameter Convolutional Neural Network (CNN) using Hyperband on the Indonesian cake dataset. The dataset is 1845 images of Indonesian snacks which consists of 1523 training data, 162 validation data and 160 testing data with 8 classes. In training data, the dataset is divided by 82% on training data, 9% validation, and 9% testing.

Result/Findings: The best hyperparameter value produced is 480 for the number of dense neurons 2 and 0.0001 for the learning rate. The proposed method succeeded in achieving a training value of 87.53%, for the validation process it was obtained 66.8%, the testing process was obtained 79.37%. Results obtained from model training of 50 epochs.

Novelty/Originality/Value: Previous research focused on the application and development of algorithms for the classification of Indonesian snacks. Therefore, optimizing hyperparameters in a Convolutional Neural Network (CNN) using Hyperband can be an alternative in selecting the optimal architecture and hyperparameters.

Optimization of the Convolutional Neural Network Method Using Fine-Tuning for Image Classification of Eye Disease

2024-03-31T18:54:09+07:00

The eye is the most important organ of the human body which functions as the sense of sight. Most people wish they had healthy eyes so they could see clearly about life around them. However, some people experience eye health problems. There are many types of eye diseases ranging from mild to severe. With advances in technology, artificial intelligence can be used to classify eye diseases accurately, one of which is deep learning. Therefore, this study uses the Convolutional Neural Network (CNN) algorithm to classify eye diseases using the VGG16 architecture as a base model and will be combined using a fine-tuning model as an optimization to improve accuracy.