Aakif Mairaj

Dr. Aakif Mairaj


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 November 2023 in Research Square
Verified
Preprint
Open access
PDF file
SSSanskriti Sanjay Kumar Singh
Sanskriti Sanjay Kumar Singh
VMVishnu Menon
Vishnu Menon
SASAJIDHA S A
SAJIDHA S A
NMNisha V M
Nisha V M
SASheik Abdullah Abbas
Sheik Abdullah Abbas
AMAakif Mairaj
Aakif Mairaj
The identification of malicious Uniform Resource Locators (URLs) plays a pivotal role in strengthening network and cyber security. Over the years, the Internet has increasingly become a breeding ground for a multitude of cybercrimes. Malicious URLs can disrupt network performance, compromise data integrity, and introduce vulnerabilities into the system, impacting the network’s overall security and reliability. Taking precautions and implementing preventative techniques is crucial for shielding users from cyberattacks. This study utilizes meta-learning, which is a machine learning technique that learns from the predictions of other machine learning algorithms to make better decisions. For a comprehensive evaluation, the ISCX-URL-2016 dataset was utilized, a resource curated by the Canadian Institute for Cyber Security. The proposed approach focuses on utilizing URL strings as the primary source of information for detecting malicious content.The performance of different machine learning algorithms, including Histogram-based Gradient Boosting Classification Tree, XGBoost Classifier, CatBoost Classifier, Random Forest Classifier and more, were compared for the detection of malicious URLs. The two best performing base classifiers were identified and evaluated as potential meta-classifiers. Various combinations of base classifiers were then tested in conjunction with these two selected meta-classifiers. A significant improvement in the accuracy was observed and the best accuracy of 98.25% was achieved using All Base Classifiers + Meta Classifier XGBoost. Closely followed by the Three Best Base Classifiers + Meta Classifier XGBoost, which achieved an accuracy of 98.2%.

24 November 2022 in Electrical Engineering
Verified
Journal Article
Closed access
PDF file
AMAakif Mairaj
Aakif Mairaj
MAM. S. Ansari
M. S. Ansari
MSManoranjan P. Singh
Manoranjan P. Singh

5 March 2025
Verified
Book Chapter
Closed access
PDF file
TBTanvi Bahedia
Tanvi Bahedia
SWSparsh Wabhale
Sparsh Wabhale
SASAJIDHA S A
SAJIDHA S A
AMAakif Mairaj
Aakif Mairaj
In the face of unprecedented threats posed by climate change and human activities to coral reefs, one of the Earth’s most biodiverse ecosystems, this work endeavors to address the critical need for accurate coral diversity monitoring and prediction. Focused on remote sensing and machine learning for coral reef analysis, highlighting the utility of species distribution modeling, the study introduced high-resolution spectral data for coral health assessment using WorldView-2 imagery. It employed deep learning for automated coral image classification, emphasizing efficiency in annotation and mosaic analysis. Additionally, it explored the use of artificial intelligence, particularly convolutional neural networks, for cost-effective coral reef monitoring and applied machine learning techniques, such as support vector machines, for predicting coral reef bleaching. While drawing inspiration from studies that utilized remote sensing, machine learning, and artificial intelligence, our research introduces novel approaches, including dynamic coral taxa prediction using random forest, decision tree, and SVM. Leveraging time series analysis and deep learning to forecast changes in coral taxa over time, the study utilized ARIMA, SARIMA, and LSTM models, incorporating environmental variables such as sea surface temperature and human impacts to improve predictive accuracy and inform conservation strategies. Building AI-based neural networks to classify the health of coral reefs and additionally utilizing explainable AI to further explain and recommend the results generated by the machine learning and deep learning models, enabling researchers and conservationists to make informed decisions and take targeted actions to preserve these vital ecosystems. Algorithms such as random forest, LSTM and simplified feed forwarding neural Network gave the best results of the models explored. By introducing this innovative methodology, our work complements and extends the existing body of knowledge, providing a proactive and comprehensive perspective on coral reef conservation. <!----> <!----> <!----> <!---->

11 April 2025
Verified
Book Chapter
Closed access
TDTirth Vishalbhai Dave
Tirth Vishalbhai Dave
SASAJIDHA S A
SAJIDHA S A
MNM. Nivedita
M. Nivedita
AMAakif Mairaj
Aakif Mairaj
Numerous amounts of work towards optimal hybrid energy allocation using PSO, HG-PSO, GA, HOMER-Pro-Software, multi-objective PSO, and many algorithms have been effectively applied. Challenges posed by seasonal variations in solar and wind power generation have not been addressed so far. A novel method of seasonal prediction of hybrid energy and optimal allocation using weighted ensembled ML models and optimization algorithms is proposed. Algorithms such as Decision Trees, Random Forest, K-Nearest Neighbors, XG Boost, Lasso Regression, and Ridge Regression are evaluated for accuracy based on which they are allocated weights and then ensembled for prediction of the renewable energy for each season. Utilization of user-input parameters, reflective of real-time environmental data on the ensembled model predicts the hybrid renewable power. Both the predicted values and the stated energy needs are required for optimal allocation with minimal deficit using algorithms: Particle Swarm Optimization, Grey Wolf Optimizer, and Lightning Search Algorithm for each season has been achieved.

1 February 2025
Verified
Book Chapter
Closed access
PDF file
SASAJIDHA S A
SAJIDHA S A
MSM. Sanjay
M. Sanjay
PMPillaram Manoj
Pillaram Manoj
SASheik Abdullah Abbas
Sheik Abdullah Abbas
PRPriyadarshini R
Priyadarshini R
AMAakif Mairaj
Aakif Mairaj