Daily Archives: May 1, 2026

Authors: Ansh Jena, Sujit Kakade, Arya Kedar

Abstract: Sentiment analysis can help track passengers’ per- ceptions and improve the service offered by an airline due to the increasing importance of social media, such as Twitter. It is about conducting a comparative analysis of three models of natural language processing, namely lexicon-based, machine learning, and transformer-based classification techniques for determining sentiments of airline tweets. Twitter US Airline Sentiment was chosen to be analyzed as it comprised labeled tweets from the major U.S. airlines. Data quality was improved by applying methods of text preprocessing, such as removing noise, tokeniz- ing, and eliminating stopwords. Lexicon-based sentiment analysis relied on VADER polarity baselines, machine-learning approach entailed extraction of TF-IDF features and further application of Random Forest classification technique while transformer model applied RoBERTa to identify the context of sentiment. As a result of the analysis, it was found out that while the lexicon model was faster and provided more easily understandable results, machine- learning model allowed identifying sentiments more accurately. Transformer-based RoBERTa performed the best in terms of handling more complex linguistic structures, such as negations and sarcasm.

DOI: https://doi.org/10.5281/zenodo.19948612

Published by: vikaspatanker

Authors: Dr. Dolley Srivastava

Abstract: The increasing problem of environmental pollution requires a new level of innovation going beyond the scope of existing monitoring systems. In this paper, we propose EnviroSense-ML – an end-to-end architecture leveraging IoT sensors together with machine learning algorithms for environmental monitoring and predictions. Our solution consists of a combination of inexpensive electrochemical sensors, LoRaWAN-based communication channels, and novel approaches in the field of hybrid machine learning techniques, which include the spatiotemporal GCN-LSTM model and CNN-BiGRU model using 8-bit quantization. The performance evaluations performed using the real-world dataset showed that our GCN-LSTM model demonstrated the highest interpolation accuracy (R² = 0.96), due to the inclusion of additional information about altitude and land cover into graph connections of the sensors. At the same time, 8-bit quantization resulted in 66% compression of the model's size with less than 1% degradation of its accuracy. Moreover, experiments showed that ML algorithms can improve sensor measurements' accuracy up to 46%. Also, our two-stage approach based on XGBoost reached near-perfect Air Quality Index prediction results (R² = 1.00, MAE = 0.35).

DOI: https://doi.org/10.5281/zenodo.19946681

Published by: vikaspatanker

Authors: Dr. Sharada H N, Dr. Sandhya S V

Abstract: Early-stage hiring processes continue to depend on resume-based and keyword-based filtering, which does not reliably capture a candidate’s actual abilities. This paper presents an AI-assisted skill evaluation system that prioritizes demonstrated performance over resume content. The system models candidate screening as a multi-stage pipeline: skill profiling, dynamic assessment delivery, automated rule-based and NLP evaluation, and weighted score aggregation. A competency model maps candidate skills to standardized assessment criteria, enabling objective cross-candidate comparison. Evaluation on simulated data (n=100) yields a Spearman rank correlation of 0.91, a false-positive shortlist rate of 12%, and a top-quintile precision of 78% — all substantially better than a conventional ATS baseline. The proposed framework is scalable, modular, and designed to reduce bias inherent in resume-centric screening.

DOI: https://doi.org/10.5281/zenodo.19946619

Published by: vikaspatanker

Authors: R.Thilakar, Dr.A.Venkatesh, Dr.M.Malarvizhi

Abstract: Maximum Power Point Tracking (MPPT) is one of the most important enablers in the field of grid-connected photovoltaic (PV) systems. This paper provides an extensive literature review on various MPPT methods used for grid-connected PV systems. The review includes both conventional approaches and advanced optimization algorithms like intelligent control schemes and metaheuristics. The article highlights some of the recent developments in the field of MPPT methods for grid-connected photovoltaic systems such as the utilization of HOA to tune fractional-order PI controllers, which can achieve a rise time of 0.0073 seconds and power generation capacity of 100.72 kW , using PSO to achieve power extraction up to 7.5% higher than P&O with only 1.54% THD, and Second Order Sliding Mode Control that achieved convergence in 0.009 seconds with 76.29% THD reduction . The comparative analysis demonstrates that although conventional methods have the advantage of ease of implementation, advanced optimization algorithms outperform in terms of faster dynamic response and global maximum point tracking.

DOI: https://doi.org/10.5281/zenodo.19946327

Published by: vikaspatanker

Authors: Dr. S. Thivyanathan, Dr. R. Anusha

Abstract: The unprecedented growth of conversational artificial intelligence agents has had a revolutionary impact on human-machine communication, but pragmatic competence—the capacity to understand and produce contextual meaning—is still an open problem for present-day technologies. This research provides a thorough linguistic study of pragmatics in human-AI interaction, which focuses on processing and producing meaning within the contexts of conversational agents' implicatures, presuppositions, speech acts, and common ground. Based on an empirical analysis of 50 transcripts of human-AI conversations, along with experimental work with 36 participants in the comparison of five conversational agents (ChatGPT-4, Google Bard, Microsoft Copilot, Claude 2, and LLaMA 2), the research concludes that although rule-based conversational agents stick to strict literal understanding, transformer models show emergent pragmatic competence through successful interpretation of indirect speech acts in 76% of the cases. However, Gricean implicatures remain difficult (recognized in only 34% of instances) and cross-turn common ground challenging (consistent in only 41% of examples).

DOI: https://doi.org/10.5281/zenodo.19946123

Published by: vikaspatanker

Authors: Mr. Abhishek Gadade, Ms. Priyanka Dharmul, Ms. Pratiksha Kamble, Prof. Krashna Rathi

Abstract: This project presents the development of a GSM-based health monitoring system using Arduino, designed to enhance patient care through real-time tracking and remote diagnostics. It integrates heart rate, temperature, and oxygen saturation sensors to continuously monitor vital signs, making it suitable for hospitals, elderly care, and home-based applications. The system displays readings on an LCD for local observation and transmits data via a GSM module to a mobile number or cloud server, ensuring remote accessibility. A buzzer alerts caregivers when any parameter exceeds safe thresholds, enabling prompt medical response. The GSM module serves as the communication backbone, facilitating SMS alerts and bridging the gap between patients and healthcare providers. The system’s modular design, centered around Arduino, allows for scalability and future upgrades such as cloud integration or mobile app support, highlighting the role of GSM technology in modern, accessible healthcare solutions.

DOI: https://doi.org/10.5281/zenodo.19942002

Published by: vikaspatanker

Authors: Hemanth KR, Abinav R, Aneesh Kumar R, Jayamoorthy S

Abstract: India's rural population continues to face substantial challenges in accessing quality digital education due to persistent structural and technological constraints. Language limitations, inconsistent internet connectivity, and the absence of reliable skill certification mechanisms significantly hinder effective learning and restrict employability. Most existing digital education platforms are designed with an urban-centric approach, assuming English proficiency, continuous online access, and high digital literacy — assumptions that exclude large segments of rural youth and lead to underutilization of rural talent despite growing demand for skilled professionals. To address these challenges, Skill Bridge is proposed as an AI-powered, multilingual digital learning platform aimed at enabling inclusive and outcome-driven skill development. The platform leverages artificial intelligence to deliver personalized learning pathways and adaptive skill assessments, ensuring learners progress systematically according to individual competency levels. Blockchain technology is further integrated to provide secure, tamper-proof, and verifiable skill certifications, thereby enhancing trust and credibility among employers. By aligning learning outcomes with job readiness and employability requirements, Skill Bridge seeks to bridge the gap between digital education and workforce participation, creating sustainable skill development opportunities for rural youth and women across India.

DOI: https://doi.org/10.5281/zenodo.19947769

 

Published by: vikaspatanker

Authors: Karan Arvindkumar Patel, Hiral Apurva Dave

Abstract: In metropolitan areas, high-rise structures are built with various irregularities in their design and loading conditions. These irregular structures can experience sudden and significant effects when subjected to different types of loads, which is why additional considerations are necessary to prevent undesirable outcomes. Past earthquakes have demonstrated the adverse consequences that can occur in such structures. To mitigate these adverse effects, nonlinear analysis techniques like the P-Δ effect have been investigated in this current study. The P-Δ effect refers to the additional actions exerted on a structure due to its deformation resulting from applied stresses. In the study, the axially loaded columns of G+18 story structures were analysed using ETABS software under nonlinear dynamic time history conditions, taking into account the influence of the P-Δ effect. The displacement and drift response analysis revealed that these values tend to be higher as the height of the structure height increases. This finding underscores the importance of considering the P-Δ effect in structural analysis. By comparing the results with and without the consideration of the P-Δ effect, it was observed that there was an approximately eight percent variation in the outcomes. This indicates that neglecting the P-Δ effect could lead to significant discrepancies in the analysis results, further highlighting its significance in accurately predicting structural behaviour.

Published by: vikaspatanker

Authors: Ashwajit Kamble, Utkarsha Lodha, Rushabh Dhakane, Prof. Kiran Khedkar

Abstract: To develop and operate an IoT-based Smart Greenhouse Monitoring and Control System, first install environmental sensors such as DHT22 for temperature and humidity, soil moisture probes, and LDRs for light intensity inside the greenhouse to continuously collect data on growing conditions. Connect these sensors to a microcontroller like Arduino Uno and integrate a WiFi module such as ESP8266 or NodeMCU to enable real-time wireless data transmission to an IoT cloud platform for remote monitoring and storage. Once data is available online, analyze it through dashboards or mobile apps to observe trends and make informed decisions. When environmental parameters deviate from optimal levels, the system should automatically trigger actuators—such as fans, sprinklers, or grow lights—to maintain ideal conditions. Throughout the cultivation cycle, data logging and analysis help identify patterns for predictive control and resource optimization, reducing manual intervention and improving crop yield and quality. The system should be operated continuously to maintain stability and can be enhanced over time by adding AI algorithms for predictive adjustments, renewable power sources for sustainability, and scalability to hydroponic or commercial setups, ensuring consistent productivity and energy-efficient farming year-round.

DOI: https://doi.org/10.5281/zenodo.19936180

Published by: vikaspatanker

Authors: Er. Sanju Surendran Girija

Abstract: Residential construction projects demand the coordinated integration of engineering execution, financial planning, architecture, and long-term usability. In many emerging economies, homeowners frequently prioritize full completion of structural, architectural, and interior works prior to occupancy. Although this approach offers immediate convenience and aesthetic satisfaction, it often imposes substantial financial pressure, accelerates decision-making under time constraints, and limits adaptability to future technological or lifestyle changes. This paper critically examines two dominant residential completion strategies: full pre-occupancy completion and phased post-occupancy development. Through engineering-economic analysis and practical construction management perspectives, the study evaluates their impacts on capital expenditure, lifecycle cost, material efficiency, flexibility, and occupant satisfaction. Findings indicate that phased completion—where essential functional systems are completed first and non-critical enhancements are deferred—can significantly improve cash flow management, reduce debt exposure, and enable future integration of advanced materials and smart technologies. The paper concludes that a hybrid strategy, combining immediate structural readiness with planned incremental enhancements, provides the most sustainable and economically rational solution for modern homeowners.

DOI: https://doi.org/10.5281/zenodo.19934779

Published by: vikaspatanker