Pneumonia remains one of the leading causes of respiratory illness worldwide and requires timely diagnosis to reduce
disease severity and mortality. Interpretation of chest X-ray images is a routine diagnostic procedure; however, manual
examination can be time-consuming and is influenced by the experience of radiologists. Computer-aided diagnostic systems
based on artificial intelligence have therefore attracted considerable attention as supportive tools for clinical decision-making.
This research presents a hybrid framework that combines deep feature extraction with traditional machine learning techniques
for automated pneumonia detection from chest X-ray images. Initially, chest X-ray images are preprocessed and analysed using
an EfficientNetV2 convolutional neural network to learn representative image features. Instead of directly performing end-toend classification, the extracted deep features are used to train three supervised machine learning classifiers: Random Forest,
Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). This hybrid strategy combines the feature
representation capability of deep learning with the classification efficiency of conventional machine learning algorithms. To
improve model transparency, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed to highlight image regions
that contribute most to the prediction. Furthermore, the selected classifier is integrated into a Streamlit-based web application
that enables users to upload chest X-ray images and obtain real-time diagnostic predictions.
Experimental evaluation demonstrates that the Support Vector Machine classifier achieved the highest performance among the
evaluated models, with an accuracy of 89.74%, precision of 86.22%, recall of 99.49%, F1-score of 92.38%, and ROC-AUC of
98.21%, indicating strong capability for distinguishing pneumonia from normal chest radiographs. The proposed framework
illustrates that combining deep feature extraction with machine learning classifiers can provide accurate, interpretable, and
computationally efficient pneumonia detection while supporting practical clinical deployment.
K. H. Veen, Pravitha R Prasad· International Journal for Re...· 0 citations
Phishing remains one of the most prevalent and financially damaging cyberattack vectors, with attackers routinely
disguising malicious links through typosquatting, homograph substitution, brand impersonation, and abuse of free top-level
domains. Existing defenses are largely reactive — blocklist services cannot flag a newly registered phishing domain until it has
already been reported, while enterprise secure-web gateways are priced for organizations rather than individual users. In this
paper, we propose RakshNet–PhishGuard, a client-first, multi-layer URL threat detection system that classifies a submitted URL
as Safe, Suspicious, or Phishing without depending on a live threat-intelligence database. Twenty-five lexical and structural
features are extracted from each URL and evaluated by two cooperating layers: a deterministic heuristic engine that checks
twelve categorical red-flag rules, and a machine-learning ensemble of six classifiers — Logistic Regression, Naive Bayes,
Decision Tree, Random Forest, Support Vector Machine, and Gradient Boosted Trees (XGBoost) — trained on a stratified 168-
URL sample drawn from the Hannousse and Yahiouche phishing-URL benchmark. A large-language-model layer (Google
Gemini, invoked through a serverless cloud function) converts the combined verdict into a plain-language explanation for nontechnical users, and a community-reporting module lets users flag suspicious URLs for analyst review. Under 5-fold stratified
cross-validation, Logistic Regression achieved the best overall performance (79.17% accuracy, 0.861 AUC), followed closely by
the Support Vector Machine (76.19% accuracy, 0.859 AUC); a Random Forest feature-importance analysis further shows that
the categorical indicators the heuristic layer specifically targets carry essentially zero learned weight in the trained models,
confirming the two layers cover complementary failure modes. The project's documented test plan, covering single and bulk
scanning, role-based access, and the AI-service fallback path, produced its expected result in all eight scenarios, with heuristic
analysis completing in under 50 ms per URL. This paper additionally positions the system against nine related works spanning
feature-engineered ML, deep representation learning, and large-language-model-assisted detection, and reports the system's
functional, non-functional, and hardware/software requirements in full. The complete system is implemented as a React 18 and
TypeScript single-page application in which every trained model runs entirely client-side, requiring no backend inference server.
Palla Srinivas, Pravitha R Prasad· International Journal for Re...· 0 citations
