Brain tumours are among the most deadly cancers and require timely and accurate diagnosis to decide on therapeutic strategies. Manual analysis of Magnetic Resonance Imaging (MRI) scans is fairly time consuming, subjective and prone to inter-observer variation. In the paper, we propose a novel deep learning framework that synergously combines the Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Explainable Artificial Intelligence (XAI) for automated multi-class brain tumour detection and classification. We propose to construct our architecture using the transfer learning paradigm, where the CNN backbone is the EfficientNet-B0 model and the transformer is the ViT-Base-Patch16-224 model, and fuse these two modules using a weighted ensemble. To obtain the proposed architecture, we are suggested to apply transfer learning by using the CNN as EfficientNet-B0 backbone and the transformer as ViT-Base-Patch16-224. Then, we adopt a weighted ensemble fusion strategy to combine these two components. Understanding the problem of class imbalance in the medical imaging datasets, we utilize the Focal Loss which is combined with comprehensive data augmentation technique Albumentations. The brain MRI is classified into 5 classes: Glioma, Meningioma, Pituitary Tumour, No Tumour. Moreover, we incorporate Gradient-weighted Class Activation Mapping (Grad-CAM) to obtain visual explanations so that experts can comprehend and validate predictions made by the model. A production-ready FastAPI backend and a React front-end interface are used to deploy the proposed system. We have conducted experiments on one standard brain tumor MRI dataset, and the proposed ensemble model outperforms the standalone CNN and ViT architectures and various state-of-the-art baselines on this benchmark dataset, with overall classification accuracy of 96.1%, F1-score of 95.8% and ROC-AUC of 0.992. This ablation study shows the contribution of individual components and demonstrates the effectiveness of the proposed multi-model ensemble with explainability.

Keywords : Brain Tumor Classification, Vision Transformer, Transfer Learning, Explainable AI, DL, MRI.

Authors : Mandapalli Sailaja , M. Sujana Priya Darshini

Title : Vision Explainable Transfer Learning for Brain Tumuor Detection and Classification

Volume/Issue : 2026;3(3 (July - September))

Page No : 68 - 77

An epidemic survey of recent years has reached a conclusion that virtually 17.9 million lives are lost annually due to disorders of the cardiovascular system and that these are the biggest killers worldwide. The power to predict cardiac defects early may have potential to decrease morbidity and provide the opportunity for timely therapeutic interventions. This study proposes an integrated computational model that incorporates traditional pattern recognition methods with neural networks using a hierarchical approach to model aggregation, with transparent mechanisms of decision attribution. Specifically, the proposed system combines a multi-layered feed-forward neural network (NN) with batch normalization and dropout layers with nine different classification algorithms--Logistic Regression, Decision Tree, Random Forest, Gradient Boosting Tree, Support Vector Machine, KNN, XGBoost, LightGBM, and CatBoost--and benchmarked them on various datasets. The best-performing models were then integrated using a hierarchical stacking model: a Logistic Regression supermodel decides whether the test sets shall be combined or not, and which members of the stacking set should indeed be in the final model. Evaluated on the Cleveland cardiac dataset on UCI repository, the proposed model can achieve 90.16% classification accuracy, 96.43% sensitivity, and receiver operating characteristic of area under the curve 0.9524 with 303 clinical records in 13 physiology attributes. Oversampling with SMOTE helps to overcome the natural class imbalance found in the training partition, and Shapley-value-based attribution provides for each patient a fine-grained reason for each prognosis prediction. The Streamlit front-end application provides a fully functional web application to help with a fast bedside risk assessment. Empirical results show that the composite model architecture consistently outperforms individual classifiers by using the minimal possible rate of overlooked positive diagnosis (one), which proves to be very critical in clinical screening situations where negative diagnosis if overlooked has life-threatening consequences.

Keywords : Transfer Learning, Ensemble Learning, Explainable AI, Grad-CAM, DL, Medical Image Analysis, MRI.

Authors : Koppadi Sowmya , P S V Krishna , P Vamsi Krishna Raja

Title : An Integrated Multi-Algorithm Computational Intelligence Framework for Cardiac Risk Prediction Through Hierarchical Model Fusion and Explainable AI

Volume/Issue : 2026;3(3 (July - September))

Page No : 57 - 67

Despite the dynamic nature of the market, large dimensionalities of asset space and varieties of financial products, portfolio optimization is a highly challenging problem. These traditional methods like Markowitz Mean-Variance Optimization and Risk Parity are highly static, and have not been able to adjust to the speed-of-change in market regimes. In this paper, the authors present a new Quantum-Inspired Portfolio Optimization (QIPO-RL) model that combines these interesting approaches to create a framework for a Reinforcement Learning (RL) based dynamic stock allocation algorithm. The framework blends quantum-inspired search techniques, an adaptive RL agent, and asset weights to maximize risk-adjusted asset returns, while maintaining assets in optimal allocation, and provides a way to rebalance a portfolio continuously in response to the changing market environment. The results from experiments were compared with state of the art baselines, which showed that QIPO-RL’s annual return is 16.8%, its Sharpe ratio is 1.61, and the maximum drawdown is 11.5% which is the best among all the competing methods. These findings support the synergism of using a global search method inspired by quantum computers in conjunction with an RL-based adaptation of decisions.

Keywords : Portfolio Optimization, RL, Quantum-Inspired Computing, Dynamic Asset Allocation, Sharpe Ratio.

Authors : Kishore Kumar Sambangi

Title : Quantum-Inspired Portfolio Optimization Using Reinforcement Learning for Dynamic Stock Allocation

Volume/Issue : 2026;3(3 (July - September))

Page No : 50 - 56

Although the performance of LLMs on a wide variety of natural language processing problems demonstrates remarkable ability, hallucinated responses are introduced as one of the key weaknesses of LLMs, especially in knowledge-intensive applications, where fidelity to facts is paramount. While effective in reducing hallucinations, the context retrieved during the RAG operations is still very often suboptimal with respect to the external documents used in the retrieval stage, and being based on cosine similarity and nearest-neighbour search, these models typically do not return optimal context to support factual generation. The authors propose a five-stage solution, called Quantum-Enhanced Retrieval-Augmented Generation (QERAG), which combines the use of a quantum-inspired probability amplitude document ranking, a Context Utility Score (CUS) optimisation engine, and a Hallucination Verification Agent (HVA) based on a formal Hallucination Reduction Index (HRI). The Quantum Relevance Score (QRS) uses interference based, Amplitude Encoding on candidate Document Sets to yield a normalised relevance distribution that emphasises the relatively higher value generated in the discriminative context as compared to other locally similar passages in a document set. QERAG outperforms Standard LLM and Traditional RAG models on all five Natural benchmark across response accuracy, with a score of 92.8% vs. 74.3%, and hallucination rate, 4.3% vs. 18.2%, respectively. They achieve a significant overall improvement by using quantum-inspired retrieval layer, which achieves a 3.5-percentage-point reduction in hallucination rate when compared to cosine-similarity RAG, with this single layer showing more reduction than the rest of the pipeline layers. The results of an ablation study show the individual contribution of every pipeline stage, and the quantum-inspired retrieval layer exhibits the greatest reduction of a 3.5 percentage points over cosine-similarity RAG.

Keywords : Quantum-Inspired Retrieval, LLM, NLP, Quantum Relevance Score, Factual Consistency.

Authors : Seepana Praveenkumar

Title : Quantum-Enhanced Retrieval-Augmented Generation for Hallucination Reduction in Large Language Models

Volume/Issue : 2026;3(3 (July - September))

Page No : 41 - 49

Web applications are ubiquitous and serve various business and technical functions. As the number of web applications continues to increase, they are also becoming one of the most common targets for cyber-attacks. This paper proposes a web application penetration testing framework that helps identify, classify, and mitigate security vulnerabilities in web applications. The proposed framework is based on the OWASP Top 10 and leverages several security tools to detect vulnerabilities with higher accuracy and a minimized number of false-positive outcomes. The proposed framework classifies detected vulnerabilities based on their categories and assigns a priority level to the detected vulnerabilities based on their risk assessment. Mitigation recommendations are also provided along with a complete security report that helps developers in strengthening the application security. The effectiveness of the proposed framework is evaluated using a number of web applications including DVWA and OWASP Juice Shop.

Keywords : Web Application Security, Vulnerability Assessment, Cybersecurity, OWASP ZAP, Burp Suite.

Authors : Sk Akbar , Devarapalli Bhasakra Venkat Sai , Md Bushra

Title : Web Application Penetration Testing And Vulnerability Mitigation Using OWASP Top 10

Volume/Issue : 2026;3(3 (July - September))

Page No : 34 - 40

In today’s kind of competitive business world, keeping existing customers is often more cost-effective than going out and grabbing totally new ones. If an organization can notice churn earlier, it can act first, rather than sitting and waiting then reacting a bit late, and in general customer satisfaction gets a stronger push. In this project, we build a machine learning system for customer churn prediction, it flags customers who are more likely to leave a service , by looking at their behaviour signals, how they actually use the service, demographic details, and also account related information. The whole workflow starts with data prepossessing, where we clean up and reorganize the dataset , then we do exploratory data analysis, just to get a better feel for customer behaviour and uncover patterns that might otherwise remain kind of unnoticed. After that, several machine learning classification algorithms are trained and tested, so we can choose the model that produces the most accurate and dependable churn forecasts. For performance checking we rely on familiar evaluation metrics like accuracy, precision, recall, F1-score, and ROC-AUC, which makes comparing results simpler and lowers the “it just seems better” bias. To avoid that “black box” feeling during prediction, the system also uses SHAP (SHapley Additive exPlanations). SHAP kind of helps interpret what each variable is contributing, by showing how different features shift the churn outcome for each individual customer.

Keywords : Customer Churn Prediction, ML, Behavior Analysis, XAI, SHAP, customer retention , Predictive Analytics.

Authors : M Swetha , Kandukuri Gowtham

Title : Customer Churn Prediction using Behavioural and usage Pattern Analysis System

Volume/Issue : 2026;3(3 (July - September))

Page No : 28 - 33

: In this paper, a general overview of the use of deep learning in the battle against the booming deepfake industry problem is discussed. Uses of deep learning include, but are not limited to, natural language processing, machine learning, and computer vision and are responsible for a multitude of novel applications. Meanwhile, the growing number of convincing videos and images has also been worrying. This technology can have serious implications online when used for nefarious purposes, such as fake news stories, persona impersonation, financial scams, and distribution of unwanted explicit visual material. Those such as celebrities and politicians are particularly vulnerable to this. The current work evaluates the performance of four deep learning models, namely InceptionResNetV2, VGG19, a standard CNN and Xception, in the fields of deepfakes generation and identification. The evaluation carried out using a Kaggle dataset of deepfakes confirms that Xception outperforms the other models analysed in detecting deepfakes. In a rapidly evolving landscape, where malicious deepfakes are becoming more common every day, it is necessary to develop dependable detection systems to reduce the impact they can have on society.

Keywords : Deep Learning, Deepfake Detection, InceptionResNetV2, VGG19, CNN, Xception.

Authors : Rama Rao Adimalla

Title : Exploring Xceptions's Effectiveness in Detecting Deep Fake For Image and Video Formats

Volume/Issue : 2026;3(3 (July - September))

Page No : 19 - 27

Lung cancer remained one of the leading causes of cancer-related mortality worldwide, making early diagnosis essential for improving treatment opportunities and patient outcomes. Computed tomography (CT) imaging became an important diagnostic modality because of its ability to capture detailed anatomical information from the pulmonary region. At the same time, advances in artificial intelligence and deep learning created opportunities for automated medical image analysis and decision support. Despite this progress, challenges, including limited labelled datasets, moderate generalisation capability, computational constraints, reproducibility concerns, and limited interpretability, continued to influence the development of reliable diagnostic frameworks. This research developed a transfer learning framework based on ResNet50 for lung cancer detection using CT scan images, evaluated classification performance through accuracy, precision, recall, and F1-score, and established a reproducible experimental baseline for future explainable and optimised diagnostic systems. A publicly available CT image dataset containing four diagnostic categories was utilised. Data preparation included image resizing, normalisation, and augmentation before model training. The experimental outcomes demonstrated progressive learning behaviour throughout training, where training accuracy reached 71.32% and validation accuracy reached 62.50%, accompanied by decreasing training and validation loss values. Evaluation on the testing dataset produced an overall classification accuracy of 57%, with weighted precision, recall, and F1-score values of 0.57, 0.57, and 0.50, respectively. Class-level analysis indicated stronger recognition performance for normal CT images and comparatively balanced detection capability for adenocarcinoma, whereas lower performance was observed for large cell carcinoma and squamous cell carcinoma. The findings suggested that transfer learning remained a practical approach for CT-based lung cancer classification under limited data conditions. In addition to experimental evaluation, the study contributed a reproducible implementation framework that may support future comparison, explainability integration, and continued optimisation of diagnostic models.

Keywords : Lung Cancer Detection, CT , ResNet50, Transfer Learning, DL, Medical Image Classification.

Authors : J.V. G. Prakasa Rao Pyla , Dr. D. Mabuni

Title : Lung Cancer Detection from CT Images Using ResNet50

Volume/Issue : 2026;3(3 (July - September))

Page No : 8 - 18

With the rapid expansion of social media and other digital platforms, the dissemination of false information through these channels has become widespread, leading to difficulties in deter-mining the authenticity of online content. Moreover, fact-checking through traditional means is very slow and cannot efficiently manage the enormous volume of information. This paper offers a deep learning-based misinformation detection system as a solution to this problem. According to the paper, the system utilizes various NLP (Natural Language Processing) techniques such as text cleaning, tokenization, and feature extraction in order to convert text data into a form that can be easily used for learning by deep learning algorithms. A Long Short-Term Memory (LSTM) deep learning model is used as the core-based encoding mechanism to capture the underlying semantics and contextual clues hidden in the text that help determine whether the text is genuine or fake. The system was subjected to a rigorous evaluation process using well-known labelled datasets while relying on widely-accepted performance metrics including accuracy, precision, recall, and F1-score. Results from the experiments indicate that the system proposed in this paper not only outperforms existing systems in terms of accuracy but also embodies an efficient, scalable, and trustworthy method for automatically detecting fake news.

Keywords : Fake News Detection, DL, NLP, LSTM, ML, Social Media Analysis, Semantic Analysis.

Authors : Md. Bushra , G Venkata Ravali , Sk. Akbar

Title : Detecting Misinformation using Deep Learning Techniques

Volume/Issue : 2026;3(3 (July - September))

Page No : 1 - 7