Authors: Chinta Lakshmi Prasanna Kumar, Dr.K.Naga Sreenivasa Rao

Abstract: This paper presents a detailed laboratory-based experimental investigation on determining the optimum replacement levels of Fly Ash and Ground Granulated Blast Furnace Slag (GGBS) as supplementary cementitious materials in concrete. Ordinary Portland Cement (OPC) was partially replaced with GGBS at levels of 5%, 6%, 7%, 8%, 9%, and 10%, while Fly Ash was incorporated at replacement levels of 20%, 40%, and 60% of the total binder content. A constant water-to-cementitious materials ratio of 0.45 was maintained for all concrete mixes to ensure uniformity and comparability of results. The study was conducted on M25 grade concrete, designed with a mix proportion of 1:1.36:2.71.

 

 

Published by: vikaspatanker

Authors: Dr. Bayomock Linwa André Claude, Mr. Bakayoko Moussa

Abstract: This project proposes an innovative architecture that aims to ensure inter-mobile network financial transactions inside a specific country or between different countries. The architecture is a micro-service oriented. The architecture uses infrastructure as mobile server, gateways, that ensure interoperability, transparency and secure transactions between 2 separate mobile operators. Web technologies have been used to implement the solution. The architecture uses foundation principles of an open, efficient and inclusive financial ecosystem.

DOI: https://doi.org/10.5281/zenodo.19063263

Published by: vikaspatanker

Authors: Mr. Dr.M.Veerabhadra Rao, Munasa Satya Bhaskar

Abstract: The increasing use of social media platforms has created vast amounts of user-generated textual data that reflect personal emotions, thoughts, and behavioural patterns. These digital footprints provide valuable insights into an individual’s psychological state and can be leveraged for early detection of mental health conditions. However, traditional mental health assessment methods rely heavily on clinical interviews and self-reported questionnaires, which may not always provide timely or scalable solutions. This study proposes an intelligent hybrid machine learning framework for early mental health risk prediction using social media text analytics. The system integrates conventional machine learning models and deep learning architectures to perform multiclass classification of mental health conditions such as anxiety, depression, stress, and other psychological states. The framework incorporates comprehensive text preprocessing techniques, including cleaning, tokenization, stop-word removal, and feature extraction using advanced vectorization methods. Multiple classifiers such as Support Vector Machines (SVM), Random Forest, Logistic Regression, XGBoost, and a hybrid BiLSTM-CNN deep learning model are implemented and evaluated. To enhance performance, the proposed system applies hyperparameter optimization and dynamic model selection strategies. Experimental results demonstrate that the hybrid framework achieves high predictive accuracy and balanced performance across precision, recall, and F1-score metrics. The system provides a scalable and automated approach for mental health analysis, offering potential support for early intervention and preventive healthcare strategies.

DOI: https://doi.org/10.5281/zenodo.19063137

Published by: vikaspatanker

Authors: Challa Prasad, Sk.Abdulkareem

Abstract: Concrete is the most widely used construction material in the world, but its inherent brittleness and low tensile strength often limit its performance in structural applications. To overcome these limitations, the addition of fibres into the concrete mix has emerged as an effective technique to improve mechanical properties such as tensile strength, ductility, toughness, and impact resistance. This study investigates the mechanical behaviour of hybrid fibre-reinforced concrete (HFRC) incorporating a combination of steel fibres and polypropylene fibres. Steel fibres are known for their high tensile strength and crack-bridging capacity, while polypropylene fibres enhance post-crack behaviour and resistance to plastic shrinkage cracking. The experimental program includes the preparation of various concrete mixes with different proportions of hybrid fibres, followed by testing for compressive strength, split tensile strength, and flexural strength. The results demonstrate that the synergistic effect of steel and polypropylene fibres significantly enhances the mechanical performance of concrete compared to conventional plain concrete and single-fibre mixes. The research highlights that an optimal hybrid fibre ratio exists, which maximizes strength and ductility without compromising workability. The study provides valuable insights for structural engineers and researchers aiming to improve the durability and performance of modern concrete structures.

 

 

Published by: vikaspatanker

Authors: Mr. G. Harsha Vardhan, Shaik Kareem Ahmed

Abstract: The rapid expansion of digital media platforms has significantly increased the spread of misinformation, posing serious threats to public opinion, political stability, and social harmony. The automated identification of fake news has therefore become a critical research challenge in the fields of machine learning and natural language processing. This paper presents an intelligent and robust fake news detection framework that leverages advanced textual feature extraction and ensemble learning techniques to improve classification performance. The proposed system incorporates comprehensive data preprocessing, including text normalization, stop-word removal, tokenization, and vectorization using TF-IDF representations. Multiple supervised machine learning algorithms such as Logistic Regression, Support Vector Machine (SVM), Random Forest, and Gradient Boosting are trained and evaluated using stratified cross-validation to ensure reliability and generalization. To enhance predictive accuracy and reduce model bias, an ensemble-based voting mechanism is employed. Performance evaluation is conducted using metrics including accuracy, precision, recall, F1-score, and ROC-AUC to address class imbalance and misclassification risks. Experimental results demonstrate that the ensemble framework achieves superior performance compared to individual classifiers, providing a scalable and dependable solution for real-time misinformation detection in digital environments. The proposed approach contributes toward building trustworthy information ecosystems through automated and explainable fake news classification.

DOI: https://doi.org/10.5281/zenodo.19062457

Published by: vikaspatanker

Authors: Mrs. M. Sujana Priyadarshini, Vinnakoti Sakyavardhan

Abstract: Brain tumour diagnosis using Magnetic Resonance Imaging (MRI) plays a crucial role in early treatment planning and patient survival. However, manual interpretation of MRI scans is time-consuming and may lead to inconsistent clinical decisions. To address these limitations, this study proposes an explainable ensemble transfer learning framework for multiclass brain tumour classification. The proposed model integrates multiple pre-trained convolutional neural network architectures and aggregates their predictions using an ensemble strategy to enhance classification robustness and reduce overfitting. Furthermore, Explainable Artificial Intelligence (XAI) techniques are incorporated to visualize tumour regions and improve model interpretability, thereby increasing clinical trust and reliability. The dataset consists of multiclass MRI images categorized into glioma, meningioma, pituitary tumour, and no-tumour classes. Data augmentation and preprocessing techniques are employed to improve generalization performance. Experimental evaluation demonstrates that the ensemble framework achieves superior classification accuracy compared to individual transfer learning models. Performance is assessed using accuracy, precision, recall, F1-score, and confusion matrix analysis. The integration of explainability tools further validates the model’s capability to focus on clinically relevant tumour regions. The proposed approach offers a reliable, scalable, and interpretable solution for automated brain tumour detection and classification, making it suitable for real-world clinical decision support systems.

DOI: https://doi.org/10.5281/zenodo.19062217

Published by: vikaspatanker

Authors: Sai Narendra Ghodke, Siddhartha V. Bhosale, Sunraj Shetty

Abstract: This paper presents APEX AI, a professional-grade equity trading signal platform designed for National Stock Exchange (NSE) listed Indian stocks. The system employs a heterogeneous ensemble of three complementary machine learning models: Gated Recurrent Unit (GRU) networks for sequential pattern capture, Temporal Convolutional Networks (TCN) for multi-scale temporal feature extraction, and LightGBM for gradient-boosted tabular learning. These models are fused through a soft-voting ensemble to produce probabilistic price forecasts expressed as P10, P50, and P90 quantile estimates over a 14-day horizon. A four-stage gate architecture governs signal quality, filtering signals based on trend alignment, volatility regime, volume confirmation, and risk-adjusted expected return. The platform exposes predictions through a FastAPI backend and a React/TypeScript/Vite frontend featuring a TradingView-style candlestick chart with an integrated forecast cone. Experimental evaluation on historical NSE data demonstrates directional accuracy above 62%, with the ensemble outperforming any individual constituent model.

 

 

Published by: vikaspatanker

Authors: Byragoni Srinivas, N.Sriaknth

Abstract: This project gives in brief, the theory behind the design of liquid retaining structure. Water tanks are storage containers for storing water. Elevated water tanks are constructed in order to provide required head so that the water will flow under the influence of gravity, the construction practice of water tanks is as old as civilized man. The water tanks project has a great priority as it serves drinking water for huge population from major metropolitan cities to the small population living in towns and villages. The main aim of this project is to understand the behavior of elevated water tank by observing the results of Bending Moment, Shear Forces, Maximum Stress, and Maximum Displacement and Design by using BIM software.

 

 

Published by: vikaspatanker

Authors: Mrs. T.Swapna Sridevi, Peddireddy Pattabhi Rama Lingeswar

Abstract: The rapid growth of digital communication platforms has significantly increased the volume of SMS and email messages exchanged daily. While these technologies enhance connectivity and information sharing, they have also become primary channels for spam, phishing, and fraudulent activities. Spam messages not only cause inconvenience but also pose serious security and privacy risks to individuals and organizations. Therefore, developing an accurate and efficient automated spam detection system has become an essential requirement. This study proposes a robust machine learning framework for intelligent classification of spam and legitimate (ham) SMS and email messages using advanced text analytics techniques. The system incorporates comprehensive preprocessing methods, including text cleaning, tokenization, stop-word removal, and normalization, followed by feature extraction using techniques such as TF-IDF and word embeddings. Multiple machine learning algorithms, including Naïve Bayes, Support Vector Machines, Logistic Regression, Random Forest, and Gradient Boosting, are implemented and comparatively evaluated. To further enhance predictive performance, ensemble learning strategies are employed to combine the strengths of individual classifiers. Experimental results demonstrate that the proposed hybrid framework achieves high accuracy, precision, recall, and F1-score across benchmark datasets. The system effectively minimizes false positives and false negatives, thereby improving reliability in real-world applications. The proposed approach contributes to the development of scalable, intelligent, and adaptive spam filtering systems capable of handling evolving spam patterns in modern communication networks.

DOI: https://doi.org/10.5281/zenodo.19061522

Published by: vikaspatanker

Authors: Dr Y Subba Reddy, A Guru Jyotshna, K Deepthi, B Paramesh, D.Siva Ganga Keerthi

Abstract: Neuroplasticity, as the name suggests, refers to the brain's remarkable ability to reorganize itself by forming new connections throughout life. Neuroplasticity has been observed to be more active in early childhood, as the processes of synaptic pruning and myelination are more active during this period. Research has shown that environmental stimulation has a direct effect on the thickness of the cortex, as well as the dendritic branching patterns of the neurons. Functional magnetic resonance imaging has shown that the brains of adults have a lot of plasticity, which enables the brains to recover from injury as well as to learn new skills. The neuroplasticity framework has a lot of implications, especially in the field of educational psychology as well as rehabilitation medicine. Experimental results using crawled Tor URL datasets demonstrate that the proposed method achieves 97.50% accuracy, outperforming conventional CNN-based deep fingerprinting techniques. Further optimization is achieved by incorporating a BiGRU layer after LSTM, enabling bidirectional feature extraction and improving prediction performance to 97.86%. Performance metrics including precision, recall, F1-score, and confusion matrices confirm the enhanced effectiveness of this methodology for distinguishing normal and attack-type Tor services, providing a robust framework for secure network monitoring.

DOI: https://doi.org/10.5281/zenodo.19060572

Published by: vikaspatanker