Web Page Blocker using Machine Learning Classifier and Chrome Plugin

In 2020, Most Filipinos are using the internet due to COVID-19 pandemic lockdowns. The internet is not limited to adults and children might be exposed to online adult content and abuse. The Philippine Internet Service providers fail to capture pornographic web pages that are not for child viewing. A Web Page classifier would help in detecting and classifying web pages. In this study, a total of 12000 web pages with adult content and academic web pages were collected using scrapy and existing datasets from DMOZ were used to create a Support Vector Machine (SVM) multi-class classifier. To improve the accuracy of the SVM model, data preprocessing was performed to remove noisy and irrelevant data from the dataset. The text in the web pages was used to train the SVM classifier by using Term Frequency and Inverse Document Frequency, Count vectorizer, and Word2vec Skip-gram embedding with TF-IDF as a multiplier. A series of experiments were conducted using multiple word embedding techniques. The SVM model built using word2vec with TF-IDF multiplier outperforms the SVM model built using TF-IDF and Count Vectorizer. The word embedding generated using word2vec was generated with a window size of 9 and a vector dimension of 900. The SVM model built using word2vec shows an S6% accuracy. The SMV model is deployed in the Django framework and a chrome plugin was created to use the SVM model using REST API. © 2022 IEEE.

Physical Distance and Crowd Monitoring System using YOLOv3

The World Health Organization advised the public that physical distancing is one of the health protocols that can minimize the spread of coronavirus disease 2019 (COVID-19). The protocol requires people to adhere to a one-meter distance from each other in public areas, thus avoiding the possible crowd formation and further spread of the virus. A software was developed to monitor the physical distance and the crowd density of a specified area or the region of interest using You Only Look Once Version 3 (YOLOv3). Video recordings, captured using mobile phones, were extracted into frames. Each video frame is then processed to a YOLOv3 model for further object detection (here-human) and implementation of physical distancing monitoring. The selected area's crowd density is also computed while considering physical distancing guidelines. If the violations in physical distance or crowd density become alarming, an email will he sent to the authorities alerting them about the occurrence of health protocol violations. Based on careful evaluation, physical distancing and crowd density violation detection has an average of 0.86 for precision, (1.81 for recall, 0.83 for F1-score, and 0.83 for accuracy. The software also successfully alerted authorities via email of the exceeding violations. The efficiency and simplicity of this approach present possible solutions for the current pandemic situation.