Crowd Counting And Density Hotspot Detection Using YOLOv11 And K-Means Clustering
Authors: Riya Abhyankar, Arundhati Melinkeri, Trupti Mahajan, Dr. Sinu Nambiar
Abstract: Urban populations are rapidly growing with large scale public events , hence monitoring the crowd behaviours and count has become a necessity for modern surveillance systems. An accu-rate crowd count helps to estimate number of people in each area while anomaly detection helps identifying situations such as overcrowding, abnormal patterns. The rpaper will present the YOLOv11 object detection algorithm and apply it with K-means clustering to count crowds and detect anomalies. The proposed system aims to provide a simple yet effective mechanism for real-time crowd analysis by leveraging detection, clustering, and visualization techniques. The experi-ment results demonstrate the ability of the system to measure crowd size and identify crowded zones, making it a useful tool for surveillance purposes in urban environments.
Artificial Intelligence And Machine Learning In Bioethanol Production: Advancing Efficiency, Sustainability, And Process Optimization
Authors: Shubhangi Baghel, Om Prakash Sondhiya
Abstract: Bioethanol has emerged as one of the most promising renewable energy sources for reduc-ing greenhouse gas emissions and decreasing dependence on fossil fuels. However, con-ventional bioethanol production systems face significant challenges, including low conver-sion efficiency, process instability, high operational costs, and limitations in feedstock utili-zation. Recent developments in artificial intelligence (AI) and machine learning (ML) have introduced advanced computational approaches capable of transforming industrial bioetha-nol production through predictive analytics, process automation, and intelligent optimiza-tion. This paper examines the role of AI and ML technologies in enhancing fermentation efficiency, optimizing biomass pretreatment, predicting ethanol yield, and improving overall sustainability in bioethanol production systems. The study also discusses key machine learning algorithms, including artificial neural networks, support vector machines, random forests, and deep learning frameworks, alongside their industrial applications. Furthermore, the paper evaluates challenges associated with data quality, computational complexity, scalability, and ethical considerations. The findings indicate that AI-driven systems signifi-cantly improve process accuracy, reduce waste generation, and enhance economic feasibil-ity. Future research directions involving digital twins, autonomous biorefineries, and ex-plainable AI are also explored.
DOI: http://doi.org/10.5281/zenodo.20225773
Comparative Process Design and Modeled Performance of a Small-Scale Bioethanol Pro-duction System Using Agricultural Residues
Authors: Samriddha Sharma, Om Prakash Sondhiya
Abstract: The increasing environmental and economic concerns associated with fossil-fuel dependen-cy have intensified global interest in renewable transportation fuels. Among alternative biofuels, bioethanol has emerged as one of the most commercially viable and widely adopt-ed options because it can be produced from renewable biomass resources and integrated into existing fuel infrastructures. This study presents a comparative process-design assess-ment of a compact bioethanol production system utilizing three abundant lignocellulosic agricultural residues: rice straw, sugarcane bagasse, and corn stover. A literature-informed process model was developed for a small-scale educational bioethanol unit comprising feedstock preparation, dilute-acid pretreatment, enzymatic hydrolysis, yeast fermentation, and reflux-assisted distillation. The investigation evaluates the influence of biomass compo-sition on fermentable sugar recovery, ethanol yield, process efficiency, and energy demand. The modeled analysis indicates that sugarcane bagasse demonstrates the most favorable conversion performance under the selected operating assumptions, yielding approximately 74 g/L fermentable sugars and 34.5 g/L ethanol prior to separation. Corn stover exhibited intermediate performance, whereas rice straw produced comparatively lower ethanol con-centrations because of its elevated ash and silica content, which reduce carbohydrate acces-sibility during pretreatment. The results further reveal that pretreatment and distillation ac-count for the majority of the process energy requirement, highlighting the importance of heat integration, solids management, and process optimization in improving system effi-ciency. The study concludes that a modular small-scale bioethanol system can serve as an effective educational and research platform for demonstrating biomass-to-fuel conversion technologies. Furthermore, transparent presentation of modeled assumptions and calculation procedures strengthens the academic reliability of design-stage biofuel studies intended for instructional and comparative analysis.
DOI: http://doi.org/10.5281/zenodo.20225753
Predicting Employee Attrition And Engagement Using Multimodal Workforce Analytics
Authors: Alka G. Saraf, J Rathnamala
Abstract: Attrition and employee engagement remain among the most pressing concerns related to human capital, directly impacting organizational effectiveness, but current techniques for predicting such outcomes rely solely on limited survey data. In this paper, we propose an end-to-end multimodal workforce analytics solution that utilizes structured HR information (employee demographics, performance evaluation metrics, remuneration), semi-structured textual information (exit interviews, management feedback), and behavioral time-series data (usage statistics of internal communication platforms and badge access logs). The proposed predictive model uses multimodal transformer with cross-modal attention techniques to jointly forecast the likelihood of employee attrition (binary classification task, AUROC = 0.89) and their overall engagement (regression task, MAE = 0.31). Tested on data collected over 18 months for 8,472 employees at a multinational IT company, our method discovers distinctive behavioral indicators, with the decrease in collaboration entropy and higher activity outside regular hours predicting attrition 12 weeks in advance. By combining NLP techniques for parsing exit interviews, we discovered that "career development opportunities" and "management competency" were the top textual predictors of leaving the job.
DOI: https://doi.org/10.5281/zenodo.20233561
Privacy Preserving Federated Or Post-Quantum Authentication Scheme
Authors: Farzeen Basith, A R Deepti
Abstract: The interplay between the advancements in quantum computing techniques and the adoption of the distributed learning approach pose an enormous challenge to conventional cryptographic authentication protocols. Traditional public key systems and federated learning (FL) authentication methods based on the hardness of solving the integer factorization problem or discrete logarithms become inefficient due to the existence of Shor’s algorithm. This paper gives a detailed review of the latest research efforts toward the development of efficient and secure privacy-preserving FL authentication methods based on Post-Quantum Cryptography (PQC). In particular, we present the state-of-the-art of three schemes, namely, PQBFL (Post-Quantum Blockchain-based Federated Learning), ZKFL-PQ (Zero-Knowledge Federated Learning with Lattice-Based Encryption), and Enhanced EAADE for vehicular networks. It is shown that lattice-based authentication is both computationally efficient (signing times of around 0.65 ms) and robust against quantum attacks. Our proposed hybrid scheme is comprised of ML-KEM for key encapsulation, ML-DSA-65 for digital signatures, and Zero-knowledge proof for gradient integrity verification. The empirical evaluation shows a reduction of 44.96% in the computation cost and 22.16% in the communication cost relative to the class.
DOI: https://doi.org/10.5281/zenodo.20233619
A Theoretical Study of Range for Energy ( 1MeV/amu to 12MeV/amu) Protons In Aluminum, Gold , Copper and Germanium Solid Materials
Authors: Wafaa N. Jasim, Faten N. Jasim, Rana K. Albonwas
Abstract: To evaluate the effects of radiation, the range of protons in the target material is an important variable for this purpose. For this study, the range of protons with energy from 1MeV/amu to 12MeV/amu which represent Within the low energy range of protons, which are of particular importance in surface applications, some are medically and technically simple. that interacts with some elements (Al,Au,Cu,and Ge) was calculated using a semi-empirical equation and compare it with SRIM2012 data ,PASTR data which they are advanced simulation tools then we use two methods of fitting : used MATLAB’s polyfit function to carry out a polynomial regression and fitting the data with a 7th-degree polynomial. The results of both methods were well agreed. Our proton range values show good agreement with SRIM2012 data and PASTR data.
DOI: https://doi.org/10.5281/zenodo.20233980
