Authors: Pratibha Kumari, Rajiv Tripathi, Snehal Ramesh, Tanvi Kapoor

Abstract: In modern enterprise IT, data protection is not merely a compliance requirement but a critical operational pillar. Backup systems such as Commvault are expected to perform with high reliability to meet recovery point objectives (RPO) and recovery time objectives (RTO). However, unpredictable backup failures continue to challenge IT operations, causing delays in restoration, potential data loss, and non-compliance with service level agreements (SLAs). Traditional monitoring and alerting are often reactive, which leaves little time for administrators to respond before a backup job fails. Predictive analytics offers a paradigm shift by enabling preemptive identification of failure patterns based on historical and real-time data. In Commvault environments, telemetry from CommServe, MediaAgents, and job logs offers rich sources for modeling and failure prediction. This review investigates how predictive analytics—particularly machine learning (ML) can be applied within Commvault environments to anticipate and mitigate backup failures. We discuss key failure types, log analysis strategies, anomaly detection, model training pipelines, and real-time visualization techniques. The integration of supervised and unsupervised ML algorithms, including regression models, clustering, and sequence prediction (e.g., LSTM), is explored for their applicability in Commvault's operational workflows. In addition, we evaluate the advantages of integrating predictive outputs into SLA-aware orchestration and automated remediation workflows. The article further contrasts Commvault’s predictive capabilities with other backup platforms and explores future research avenues in deep learning, AIOps, and federated modeling for distributed environments. By aligning predictive insights with operational pipelines, enterprises can achieve proactive data protection, reduce downtime, and improve compliance readiness in a cost-effective manner.

DOI: https://doi.org/10.5281/zenodo.15845638

Published by: vikaspatanker

Authors: Vaishnavi Kane, Assistant Professor Dr. Suhas Mache, Assistant Professor Dr. Arshiya Khan

Abstract: In the modern business environment, accurate sales forecasting is essential for effective decision-making. This paper explores the integration of time series forecasting techniques with Business Intelligence (BI) tools, specifically using Microsoft Power BI, to build an interactive dashboard for sales prediction. We present a model that combines statistical forecasting methods with data visualization to enhance decision-making in sales management. The system is designed to provide real-time insights, support strategic planning, and identify sales trends through dynamic dashboards. Our case study demonstrates that integrating forecasting models within BI platforms significantly improves sales predictability and operational efficiency. This study explores the integration of time series forecasting techniques with Microsoft Power BI to build a dashboard that predicts future sales. By combining forecasting models like ARIMA and Prophet with Power BI’s interactive features, the system enables better business decision-making. The dashboard allows users to visualize historical trends and forecasted sales data in real time.

Published by: vikaspatanker

Authors: Harsha Sammangi, Aditya Jagatha, Hari Gopal Maddireddy

Abstract: This study presents a sentiment-driven Decision Support System (DSS) that leverages advanced word embedding techniques—Word2Vec, GloVe, and BERT—to analyze CEO earnings call transcripts and predict stock market reactions. Tra- ditional lexicon-based sentiment models fail to capture the nuanced, contextual language used by executives. By employing pre-trained embeddings and machine learning classifiers, the study enhances the accuracy of sentiment classification. The proposed system integrates quantitative sentiment scores with event study method- ology to assess the impact of CEO tone on stock performance. Thematic analysis further enriches interpretability by identifying recurring patterns in executive com- munication. Results demonstrate that positive CEO sentiment generally correlates with stock appreciation, while negative sentiment aligns with declines. Among models tested, BERT outperformed others in classification accuracy. This research contributes to real-time financial analytics by embedding sentiment intelligence into DSS frameworks, supporting investors, analysts, and automated trading sys- tems with improved decision-making capabilities grounded in contextual linguistic analysis.

DOI: https://doi.org/10.5281/zenodo.15845150

 

Published by: vikaspatanker

Authors: Jinta Johnson, Assistant Professor Athira B, Professor Dr. Shine Raj G

Abstract: This paper presents a lightweight and intelligent system for the automatic extraction of structured information from academic research papers in PDF format. The proposed system leverages Natural Language Processing (NLP) techniques, TF-IDF-based summarization, and Sentence-BERT semantic similarity to extract and analyze metadata such as title, authors, organizations, keywords, and references. Built using Python and Streamlit, the tool allows users to upload PDF documents, parse academic content, and interactively review summarized metadata, references, and semantic relevance—all in real-time. This paper details the system architecture, implementation pipeline, challenges, and experimental results, demonstrating its effectiveness and scope for future enhancements

 

 

Published by: vikaspatanker

Authors: Anant Kumar, Professor Gulfam B. Shaikh, Professor Dilip L. Jade

Abstract: With the rapid urbanization of rural regions in India, the demand for healthcare infrastructure has surged dramatically. This research paper explores the architectural planning and design of a Multi-Speciality Hospital in Sikandarpur, Bihta, Patna (Bihar)—a region currently underserved in medical facilities. Emphasizing healing environments, sustainable strategies, patient-centered design, and technological integration, the paper outlines the necessity, process, and architectural responses to contemporary hospital design. A case study of Tata Medical Centre, Kolkata informs the practical and structural feasibility of the proposed design.

Published by: vikaspatanker

 

Lakshmi Kalyani Chinthala
Affilation:	Strategic Planning Program Manager San Francisco California
Email-Id:	chinthalakalyani01@gmail.com
Publication: Chinthala, L. K. (2021). Future of supply chains: Trends in automation, globalization, and sustainability. International Journal of Scientific Research & Engineering Trends, 7(6), 1-10. Chinthala, L. K. (2021). Diversity and inclusion: The business case for building more equitable organizations. Journal of Management and Science, 11(4), 85-87. Chinthala, L. K. (2021). Business in the Metaverse: Exploring the future of virtual reality and digital interaction. International Journal of Science, Engineering and Technology, 9(6). ISSN (Online): 2348-4098. Chinthala, L. K. (2025). Consumer experience 2025: The role of personalization and AI in shaping business strategies. International Journal of Modern Science and Research Technology, 3(5), 21–27. Chinthala, L. K. (2025, February). Artificial intelligence in business strategy: Enhancing competitive advantage through machine learning. International Journal of Modern Science and Research Technology, 3(2), 83–90.

 

Published by: vikaspatanker

Authors: Megha Birthare, Neelesh Jain

Abstract: The global rise in social media usage has led to a surge in unwanted bulk SMS, necessitating the development of an effective system to filter out these messages. The most prevalent issue on the internet is spam text messages. Sending a spam-filled SMS is a straightforward task for spammers. Spammers are able to take valuable data, including contacts and files, from our devices. In recent years, several word embedding techniques leveraging deep learning have been developed. These advancements in word representation could offer a reliable remedy for these problems. This study will look at a technique that employs natural language processing to distinguish among spam and ham texts utilizing the SMS Spam Collection Dataset from the UCI Machine Learning Repository. We compared the accuracy and outcomes of using the Bi-LSTM and LSTM. The effectiveness of the dataset is assessed using measures like F1-score, recall, and accuracy. The study demonstrates that the dataset's overall accuracy increases when Bi-LSTM classification is used. Python is used for all work, and a Jupyter notebook is used for implementation.

DOI: https://doi.org/10.61137/ijsret.vol.11.issue4.114

Published by: vikaspatanker

Authors: Ms.T. Nandhini Supervisor Assistant Professor, M.Mugesh Kumar, M.Snekan, R.Tamilselvan

Abstract: This project presents a machine learning-based methodology for student performance prediction with Random Forest and Feature Engineering. Academic institutions are becoming more dependent on data-driven intelligence to enhance educational planning and student support. Conventional models usually do not capture various student characteristics like demographic, academic, and behavioral features, thus restricting predictive capabilities. In this paper, we overcome these limitations by suggesting an ensemble learning approach with sophisticated feature engineering to enhance the interpretability and flexibility of the prediction process. The Random Forest classifier is employed due to its high accuracy and stability, and the model is assessed using metrics like accuracy, precision, recall, and F1-score. Experimental results indicate that the new system surpasses conventional AFSA-based models in detecting at-risk students, allowing for early intervention approaches to improve academic performance.

DOI:

 

Published by: vikaspatanker

Authors: G.Srikanth, Assistant Professor M.Harish Kumar

Abstract: Since the subgrade is the bedrock upon which the pavement model is built, its behaviour is crucial to the design of flexible road projects. Therefore, pavement performance and design analysis need a considerable deal of attention. The expansive soils include a high concentration of clay and silt, hence it is necessary to stabilise or compact the soil subgrade prior to building a flexible pavement. Subgrade soil replacement is the method of choice for stabilising certain types of soils. Fly ash, an industrial waste product, is currently being used in around 55% of its total capacity. Substituting bitumen-coated chicken mesh with fly ash in subgrade at varying percentages and layering the mesh appropriately will make good use of the fly ash. A better California bearing ratio can be achieved by using bitumen-coated chicken mesh as extra reinforcement. This study utilises the CBR mould to impact fly ash samples till they reach their maximum dry density and optimal moisture content. The samples are then used with or without bitumen coated bamboo meshes and chicken mesh layers. Dimensions of the chicken mesh match those of the CBR mould in plan view. It was thereafter covered with chicken mesh after being placed in the preparations of 1, 2, 3, and 4 layers. The laboratory tests show that the mixture with four layers of bitumen-coated chicken mesh and a 15% substitution of fly ash has the highest CBR value, indicating that it is very strong. The soil's moisture content is lowered by using plastic garbage as a partial replacement. In this study, various percentages of plastic garbage are introduced to soil in order to quantify and compare the values of UCS, CBR, MDD, and OMC with the unmodified soil.

Published by: vikaspatanker

Authors: B.Lavanya, Assistant Professor M.Harish Kumar

Abstract: This study stabilized two potentially hazardous industrial waste materials—Fly Ash (FA) and Lime Sludge (LS)—using Commercial Lime (CL) and Gypsum (G), respectively. The FA and LS come in large quantities from thermal power plants and water treatment plants, and they pose environmental hazards. The goal was to make the sludge and FA suitable for use in Civil Engineering construction applications. Tests for Unconfined Compressive Strength (UCS), California Bearing Ratio (CBR), and Split Tensile Strength Test (STS) were conducted on 39 different combinations of FA, LS, CL, and G. Using these metrics, we were able to determine that two composites stabilized with 12%CL and 1%G performed admirably: (optimum mix 2, 50%FA+50%LS) and (optimum mix 1,95%FA+5%LS). After 28 days of curing, the UCS for optimal mix 1 was 6.6 MPa, while for optimum mix 2 it was 5.8 MPa, and for STS it was 1.3 MPa, and for both mixes it was 1.1 MPa. After 28 days of curing, the optimal mix 1 had a soaked CBR value of 75% and an unsoaked value of 89%. When optimal mix 2 was cured for 28 days, the CBR values were 91% for the unsoaked condition and 82% for the soaked condition. When tested for durability according to both British and American standards, both composites passed with flying colors. For instance, following twelve cycles of wetting and drying, mix 2 samples lost 1.05% of their initial weight while mix 1 samples only lost 1.12% of their initial weight, both of which were well within the criteria that were recommended. Also, after 28 days of curing, the composites had almost little heavy metal content leaching out. Additionally, scanning electron microscopy (SEM) and X-ray diffraction (XRD) were used to study the development of cementitious compounds during curing. Having said that, the stabilized composites exhibited brittleness. The ductility and strength were examined after adding fibers to these composites in an effort to reduce their brittleness. The results of the trials with the various fiber percentages showed that adding 0.3% of fiber to both composites increased the mix's strength and ductility. The strength index and deformability index were used to measure the improvement in ductility and strength, respectively. There is an 80% increase in failure strain and a 40% increase in strength when fibers are added. The findings indicated that using Composites have achieved the necessary strength, durability, and ductility to be used as base course layer materials in flexible pavements. Furthermore, it is recommended that the total pavement thickness be decided upon based on dependability, taking into account the uncertainty in the input data such as the design traffic load (measured in Million Standard Axle, MSA) and soil carrying capacity (measured in CBR value). In order to determine the total thickness of the flexible pavement that can guarantee a specific degree of dependability in the pavement's performance, design charts were produced, taking into account the uncertainty in the input data. In addition, the reliability-based technique—which combines the Mechanistic- Empirical approach with Monte Carlo Simulation (MCS) and the First Order Reliability Method—was used to study the uncertainties in distress analysis of flexible pavement, specifically with regard to fatigue and rutting failure. In order to determine the pavement's performance, the reliability index (β) was calculated and strain at crucial sites for fatigue and rutting failure was calculated using PLAXIS 2D coding software on a three-layered flexible pavement model. The specified strength, durability, and ductility requirements are met by the produced composites, namely Optimal Mix 1 [(95%FA+5%LS), 12% CL, 1% G and 0.3% F] and Optimal Mix 2 [(50%FA+50%LS), 12% CL, 1% G and 0.3% F]. The compressive strain value at the crucial point was found to be ɛc = 13.42 x 10-5 and the tensile strain value at the same region was found to be ɛt = 18.11 x 10-5 for a 450 mm thick foundation of optimal mix 2. For 10 MSA of design traffic load, the pavement performed admirably (βR and βF >5) according to the probabilistic based methodology. However, when subjected to larger traffic loads, the pavement exhibited above-average performance in terms of fatigue and rutting.

Published by: vikaspatanker