Boarding House Renting Price Prediction Using Deep Neural Network Regression on Mobile Apps

Boarding house is the most important requirement, especially for college students who live far away from the city, place of his origin or house. However, the problem we see now is the uneven distribution of study places in Indonesia which 75% of the best top educational institutions come from the island of Java. So, students who are looking for boarding houses rent requires more effort in comparing the various aspects desired. They need to survey one by one to the boarding house they want, even though they can survey online, it still requires more effort to pay attention to the desired facilities one by one. Therefore, we then created an Mobile Application that can predict prices based on student needs by comparing several variables, namely city, area, type of boarding house, and facilities. So, students can easily estimate the ideal price. The results of this study prove that we have succeeded in predicting prices for boarding houses rent well based on the variables we have determined, and modeling that variables using Deep Neural Network Regression.

Image Captioning with Attention for Smart Local Tourism using EfficientNet

Smart systems have been massively developed to help humans in various tasks. Deep Learning technologies push even further in creating accurate assistant systems due to the explosion of data lakes. One of the smart system tasks is to disseminate users needed information. This is crucial in the tourism sector to promote local tourism destinations. In this research, we design a model of local tourism specific image captioning, which later will support the development of AI-powered systems that assist various users. The model is developed using a visual Attention mechanism and uses the state-of-the-art feature extractor architecture EfficientNet. A local tourism dataset is collected and is used in the research, along with two different kinds of captions. Captions that describe the image literally and captions that represent human logical responses when seeing the image. This is done to make the captioning model more humane when implemented in the assistance system. We compared the performance of two different models using EfficientNet architectures (B0 and B4) with other well known VGG16 and InceptionV3. The best BLEU scores we get are 73.39 and 24.51 for the training set and the validation set respectively, using EfficientNetB0. The captioning result using the developed model shows that the model can produce logical caption for local tourism-related images