Publications
Ribonucleic Acid (RNA) Cancer Clustering Using Directional Local-Binary-Pattern and Self-Organizing Map Network (SOM)
May 30, 2025Journal Journal of Internet Services and Information Security (JIS
DOI 10.58346/JISIS.2025.I2.009
Volume 15
This study helps medical professionals to find out the genetic information related to five types of cancer. The information stored in RNA is characterized by its abundance, which is responsible for forming proteins in the human body. If there is any harm in this acid, this leads to the formation of cancerous diseases. The RNA contains huge numbers of genes so It is difficult for researchers to isolate the affected genes from the healthy genes. This paper presents a method for clustering the mutated genes for five types of cancer by using a novel feature extraction method with one of the traditional unsupervised machine learning algorithms (Self-Organized Map SOM). The proposed feature extraction method is called the Bi- directional Local-binary-pattern Signal (BLS), it is inspired from three traditional feature extraction methods named the Local Binary Pattern (LBP), Local Line Binary Pattern (LLBP), and Enhanced One-dimensional Local Binary Patterns (EOLBP) to extract the important textures for five types of cancer genes. This method finds the average for both direction features of a specific window in the RNA gene sequence and slides this window along the RNA to extract the features that are the most indicative features of cancerous genes. This study successfully clustered five types of cancer genes using the SOM classifier based on the features extracted by the proposed method. The study used a benchmarked dataset to test the proposed method. The accuracy for distinguishing the muted genes using the proposed method is 99.5%.
Multi-objective Optimization in Satellite-Assisted UAVs
Feb 4, 2025DOI https://doi.org/10.54216/JISIoT.150213
Securing IoT through Intrusion Detection Systems: An Overview
Jan 17, 2025DOI https://doi.org/10.54216/JISIoT.150213
Reinforced Deep Learning for Verifying Finger Veins
Jul 2, 2021DOI https://doi.org/10.54216/JISIoT.150213
Recently, personal verifications become crucial demands for providing securities in personal accounts and financial activities. This paper suggests a new Deep Learning (DL) model called the Re-enforced Deep Learning (RDL). This approach provides another way of personal verification by using the Finger Veins (FVs). The RDL consists of multiple layers with a feedback. Two FV fingers are employed for each person, FV of the index finger for first personal verification and FV of the middle finger for re-enforced verification. The used database is from the Hong Kong Polytechnic University Finger Image (PolyUFI) database (Version 1.0). The result shows that the proposed RDL achieved a promising performance of 91.19%. Also, other DL approaches are exploited for comparisons in this study including state-of-the-art models.