Deep learning is a set of machine learning algorithms that attempt to model high-level abstractions in input data using multiple non-linear transformations. Some of the major advances in deep learning have been made in speech recognition, computer vision, and natural language processing. Considering that data volume is growing exponentially, deep learning is becoming increasingly important in the predictive analysis of big data. I have tried to collect and curate some publications form bioRxiv that related to the deep learning application in biology, and the results were listed here. Please enjoy it!
Object detection is part of the computer vision tasks related to identify or detect an object from an image or video. I have tried to collect and curate some Python-based Github repository linked to the object detection task, and the results were listed here. Please enjoy it to support your research about object detection using Python!
Abstractive summary is a technique in which the summary is created by either rephrasing or using the new words, rather than simply extracting the relevant phrases. I have tried to collect and curate some publications form Arxiv that related to the abstractive summarization, and the results were listed here. Please enjoy it!
Development of Typographical Error Identification Application in Indonesian Language Using Jaro-Winkler Distance Algorithm
Text is one of the media used by humans to communicate and interact every day, especially in the field of education, for example, in writing a final project report. The most common thing in writing text is typographical errors. Based on these problems, an application is needed to help the writer to be able to identify typographical errors in the Indonesian Language document. The application developed using Laravel version 5.8 for web application and Python version 3 for processing datasets, developing model, and developing web services. Model built uses the NLTK library and Jaro-Winkler distance algorithm implemented using the pylibjaro library. The dataset uses an open-source dataset in the form of a list of words from KBBI. This application only supports pdf files. The results of the model are applied to the web services with output in the form of JSON data. The JSON data contains a list of words that have true or false values, the number of document words, the number of correct words, the number of incorrect words, and the time of program execution.
I will use this site to inform you about my academic journeys, includes teaching, research, publication, and other academic activities like fellowship.