With the growing density of the population, traffic congestion, and changing conditions of disasters in smart cities, the emergency evacuation is one of the most significant challenges in the modern smart city. In a high event like a flood, earthquake and industrial accident or an urban fire, traditional routing solutions often do not adjust. In this paper, the authors consider the framework of Quantum-Inspired Multi-Agent Emergency Evacuation Planning (QMAEP), which is based on a combination of quantum-inspired optimization and collaboratively intelligent multi-agents to effectively facilitate the adaptive real-time evacuation management. The framework links disaster detection, city-state monitoring, route optimization, traffic management, coordinated decision making and generates safe and efficient evacuation planning under dynamic conditions. QMAEP achieves widespread coverage of the population, road safety, and reduces road congestion at minimum evacuation time. Systematic experiments illustrate the reduction of up to 44% in evacuation time and 94% in population coverage achieved by QMAEP through applying SUMO-based traffic simulations and smart city disaster scenarios. The proposed plan was a major step toward the development of next-generation disaster response facilities.

Keywords : Multi-Agent Systems, Smart Cities, Disaster Management, Adaptive Routing, IoT, SUMO simulation.

Authors : Praveen Kumar Maharana

Title : Quantum-Inspired Multi-Agent Emergency Evacuation Planning for Smart Cities

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

Page No : 78 - 85

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