INFOCOMP Journal of Computer Science

Malicious URL Detection to Avoid Web Crime Using Machine Learning Techniques

DR A RAJESWARI, MONIKA S, NIVETHA G, SANGEETHA DEVI G — Sun, 07 Jan 2024 00:00:00 -0300

Today the foremost necessary concern within the field of cyber security is finding the intense issues that create loss in secure data. In recent years, most offensive strategies are applied by spreading malicious and phishing URLs. An accidental visit to a malicious website will trigger pre-designed criminal activity. The phishing website has evolved as a serious cyber security threat in recent times. Phishing may be a type of online fraud wherever a spoofed website tries to gain access to user's sensitive data by tricking the user into believing that it's a benign website. ML algorithms are one of the effective techniques for malicious website detection. The proposed system detects whether the link is legitimate or malicious not based on varied discriminative options and attributes of the address. This application is enforced with the assistance of Gradient Boosting classifier. The model can find whether the address is safe or unsafe.

A Modified Dense-UNet for Pulmonary Nodule Segmentation

Najme Zehra Naqvi, Muskaan Chhikara, Arushi Garg, Yashika, Milan Agrawal — Sun, 07 Jan 2024 00:00:00 -0300

Lung cancer continues to be a major health concern worldwide, taking countless lives every year. Although the detection of lung nodules has been made versatile by using CT scans, radiologists require certain assistance to make this process faster and more efficient. This need led to the introduction of Computer Aided Diagnosis (CAD) and then, deep learning into the healthcare field. In this work, we have proposed a modified 2D Dense-UNet model for the segmentation of lung nodules from the CT scan images. The model is trained and tested on the LUNA16 dataset which is publicly available. Through the addition of Squeeze & Excitation (SE) blocks and the GeLU activation function in its dense layers, some improvement has been observed in the basic model. Furthermore, we have also compared our suggested model's performance to that of various other 2D deep learning networks on the basis of their Dice Coefficient (DSC).

Deep-CodecG*: A Generalized Deep Autoencoder for Robust Segmentation of Left Atrium in Cardiac MRIs

Akhilesh Rawat, Rajeev — Sun, 07 Jan 2024 00:00:00 -0300

The left atrium receives oxygenated blood from pulmonary veins and is a vital organ concerning
congestive heart failure. Several deep learning-based architectures and learning methodologies have
been proposed for left atrium semantic segmentation. These studies have shown good performance in
learning known datasets. However, generalization remains challenging. In this work, we propose a deep
auto-encoder architecture with generalization ability which we call Deep-CodecG*. The proposed model
utilized a CNN-based auto-encoder in which the standard convolution is replaced with a two-convolution
layer block. This proposed model is generalization enabled with a proper parameterization for (near-)
optimal performance. The proposed Deep-CodecG* improves performance on unseen test data, a dice
score of 0.95, which is 6.3% higher than that of a standard auto-encoder. The proposed model gave higher
sensitivity, specificity, Jaccard, and structural similarity values and lower Hausdorff distance indicating
improvement over an autoencoder with similar two-convolution layer blocks. Though these quantitative
improvements seem marginal, they are shown to have a significant impact. The segmented left atrium
images match the ground-truth data very closely. Thus, the proposed Deep-CodecG* architecture for left
atrium segmentation exhibits well-generalized and robust performance over various image datasets

Enhancing Document Digitization: The All-in-One ‘Document World’ App

Tanmay Kadam, Akash Jathar, Pratosh Bhiugade, Darshan Parab, Nitin Shivsharan — Sun, 07 Jan 2024 00:00:00 -0300

The aim of this article is to provide assistance to students, employees, and the general public through the
use of document scanning, Optical Character Recognition (OCR), QR generation, and QR reading. With the increasing
trend of digitalization in educational institutions, offices, and governments, there is a constant need for tools that can
help us accomplish these tasks. To facilitate this process, we require a reliable scanning app with features like PDF tools,
QR generator, and QR reader. While numerous apps are available online, they often lack in quality and some functions,
or require payment for advanced features. However, the “Documents World App” provides a solution with its quality
scanning, PDF tool options for modifying existing PDFs, and editing options for adding signatures and watermarks,
which simplifies our work. This app offers advanced functionalities, such as text extraction with the help of the itext
library, that are not typically available in widely used tools like ”Adobe Scan” and ”iLove PDF”. Furthermore, we aim
to provide this service to all users without any charge and the add free.

Review On The Analysis Of Qoe Applied In Serious Virtual Reality Games

Demostenes Zegarra Rodriguez, Fernando Caio SILVA AMARAL — Sun, 07 Jan 2024 00:00:00 -0300

Over time, electronic games have evolved from simple pixelated objects to complex expe-
riences with a wide variety of narratives and user interactions, including various forms of immersion
such as customized controls and games utilizing virtual reality (VR). VR allows users to interact with
and perceive virtual objects in a more immersive way. Transitioning beyond mere entertainment, games
have proven to be excellent educational tools for teaching various subjects and assisting in tasks like
professional training across diverse fields, known as serious games. Through the use of virtual reality,
individuals can visually learn through experiences such as virtual trips to aquariums, museums, and even
the lunar surface. Healthcare professionals can practice surgical techniques using virtual patients, and
production industry workers can operate machines without the need to halt real factory machinery for
training purposes. While this technology is considered revolutionary by some, certain factors still hinder
the widespread adoption of virtual reality by the general population. One primary concern reported by
VR users is the occurrence of motion sickness and discomfort. Research is underway to enhance the user
experience, but this remains an open challenge. Addressing this issue, user experience (QoE) research
can be applied to assess and identify improvements. Thus, QoE enhancements not only contribute to
user satisfaction but also maximize the educational benefits of these games. This study aims to evalu-
ate key user complaints regarding the experience with specific games. Once these issues are identified,
suggestions will be implemented, and a new round of user game experimentation, along with feedback
collection, will be conducted. This refinement process is intended to be repeated iteratively, allowing the
results to guide improvements in the Quality of Experience for serious games.