Applied Science and Engineering Journal for Advanced Research <p>Applied Science and Engineering Journal for Advanced Research is a bi-monthly, online, double blind peer reviewed open access international journal. This journal publish research papers from all the discipline of applied sciences, Medicine and engineering related subjects. Published papers are freely accessible online in full-text and with a permanent link to the journal's website.</p> <p><strong>JOURNAL PARTICULARS</strong></p> <p><strong>Title:</strong> Applied Science and Engineering Journal for Advanced Research<br /><strong>Frequency:</strong> Bimonthly (6 issue per year)<br /><strong>ISSN (Online):</strong> <a href="" target="_blank" rel="noopener">2583-2468</a><br /><strong>Publisher:</strong> Singh Publication, Lucknow, India. (Registered under the Ministry of MSME, Government of India. Registration number: “UDYAM-UP-50-0033370”)<br /><strong>Chief Editor:</strong> Dr. Ashutosh Kumar Bhatt<br /><strong>Copyright:</strong> Author<br /><strong>License:</strong> Creative Commons Attribution 4.0 International License<br /><strong>Starting Year:</strong> 2022<br /><strong>Subject:</strong> Applied Science and Engineering <br /><strong>Language:</strong> English<br /><strong>Publication Format:</strong> Online<br /><strong>Contact Number:</strong> +91-9555841008<br /><strong>Email Id:</strong><br /><strong>Journal Website:</strong> <a href=""></a><br /><strong>Publisher Website:</strong> <a href="" target="_blank" rel="noopener"></a><br /><strong>Address:</strong> 78/77, New Ganesh Ganj, Opp. Rajdhani Hotel, Aminabad Road, Lucknow-226018, Uttar Pradesh, India.</p> Singh Publication en-US Applied Science and Engineering Journal for Advanced Research 2583-2468 Password Complexity Prediction Based on RoBERTa Algorithm <p>Corresponding author email: In the digital age, password security is a top priority for protecting personal information. Machine learning techniques provide us with intelligent and efficient means to enhance password security. In this paper, we adopt RoBERTa algorithm and use the password complexity text dataset for password complexity prediction, and the confusion matrix and accuracy rate of the three classifications are derived through two model trainings. The confusion matrix shows that the vast majority of the classification results are accurate, and the accuracy of the two classifications is over 99.741% and 99.11%, respectively. This indicates that the model is able to effectively predict password complexity, provide users with accurate feedback, and prompt users to enhance password security in a timely manner. Through this study, we can better understand how to use machine learning technology to improve password security and protect personal private information from malicious intrusion. In our daily life, we should pay attention to the complexity of password settings and realise the importance of password security for personal information protection. We look forward to the launch of more similar studies in the future to further strengthen cybersecurity protection measures and work together to build a more secure and reliable digital environment.</p> Yuhong Mo Shaojie Li Yushan Dong Ziyi Zhu Zhenglin Li Copyright (c) 2024 Yuhong Mo, Shaojie Li, Yushan Dong, Ziyi Zhu, Zhenglin Li 2024-05-11 2024-05-11 3 3 1 5 10.5281/zenodo.11180356 Spam Detection and Classification Based on DistilBERT Deep Learning Algorithm <p>This paper discusses the importance of spam classification in the field of information security. With the popularity of the Internet and email, spam has become one of the major issues affecting user experience and information security. The study begins with preprocessing text data in various ways, including converting to lowercase, removing irrelevant content, links, punctuation, etc., and filtering deactivated words and words of length 1. By applying the DistilBERT model to the text classification task, the results show that it achieves 93% accuracy in spam classification, effectively distinguishing between spam and non-spam emails. The confusion matrix showed that 18,500 emails were correctly classified and a small number of spam emails were misclassified as non-spam emails. Overall, the DistilBERT model showed high accuracy in spam classification, but more algorithms are still expected to emerge to improve the prediction accuracy. This study provides a useful reference for improving spam filtering systems in the future, which is expected to further enhance user experience and information security.</p> Tianrui Liu Shaojie Li Yushan Dong Yuhong Mo Shuyao He Copyright (c) 2024 Tianrui Liu, Shaojie Li, Yushan Dong, Yuhong Mo, Shuyao He 2024-05-11 2024-05-11 3 3 6 10 10.5281/zenodo.11180575 Comprehensive Analysis of Recent developments of control strategies and Modular Multilevel Converter for HVDC <p>The growing need for Renewable Energy Sources (RESs) has made Wind Energy Conversion Systems (WECS)—that is, systems that use Modular Multilevel Converters (MMC) and Doubly Fed Induction Generators (DFIG)—essential components of modern power generation. Although these systems have advantages including enhanced grid integration and variable-speed operation, complex control techniques are required to realize their full potential. This requirement is acknowledged in the proposed study, which also presents proportional-integral (PI) and particle swarm optimization (PSO) controllers as essential components of an advanced control system. Optimizing WECS performance is the major goal, with a focus on achieving and sustaining a steady DC link voltage. In order to ensure overall system reliability and efficiency, DC link voltage stability is crucial, especially when using High-Voltage Direct Current (HVDC) technology to transmit electrical power across long distances. The MATLAB Simulink platform is employed to demonstrate the efficacy of the suggested work.</p> Patra Gowtami Dr. J. Ramakant Copyright (c) 2024 Patra Gowtami, Dr. J. Ramakant 2024-05-24 2024-05-24 3 3 11 19 10.5281/zenodo.11280078 Lidar and Monocular Sensor Fusion Depth Estimation <p>In this project, we present a novel approach to depth perception using a monocular camera by incorporating information from both RGB and LiDAR modalities. Our primary objective is to investigate the performance and effectiveness of different techniques to generate accurate depth estimation. We first implemented the Swin Transformer-based depth estimation model and evaluated its performance on KITTI dataset containing RGB images and their corresponding ground truth depth maps. Next, we proposed an RGB-LiDAR fusion model. We performed necessary preprocessing steps on the dataset, such as resizing, normalization, and data augmentation, and trained both models with identical configurations for a fair comparison. Our results demonstrate that the proposed RGB- LiDAR fusion model achieves superior depth estimation performance compared to the original Swin Transformer based model. We evaluated the models on the test dataset using metrics such as mean absolute error (MAE) and root mean squared error (RMSE). The enhanced performance indicates the potential benefits of RGB-LiDAR fusion for monocular depth perception tasks. This study offers valuable insights into the strengths [<a href="#_bookmark0">1</a>] and weaknesses of combining RGB and LiDAR inputs and lays the foundation for future research in monocular depth perception, aiming to further improve model architectures and training techniques.</p> Shuyao He Yue Zhu Yushan Dong Hao Qin Yuhong Mo Copyright (c) 2024 Shuyao He, Yue Zhu, Yushan Dong, Hao Qin, Yuhong Mo 2024-05-27 2024-05-27 3 3 20 26 10.5281/zenodo.11347309 Text Sentiment Detection and Classification Based on Integrated Learning Algorithm <p>The aim of this paper is to explore the importance of textual sentiment detection in the field of Natural Language Processing and to classify and detect sentiment through various machine learning algorithms. Firstly, we train using Park Bayes, Random Forest, XGB and Support Vector Machine models, and then integrate them into a voting classifier for comparative analysis. The results show that the Random Forest model performs the best in the training set; and in both the validation set and the test set, the accuracy of the voting classifier is the highest, reaching 93.32% and 94.47%, respectively, which shows its superiority in the classification of text sentiment detection. Taken together, voting classifier has the best prediction results and provides an effective solution for text sentiment detection. This study not only provides an in-depth comparative analysis of the performance of different machine learning algorithms in text sentiment detection, but also provides a useful reference for subsequent related research and applications.</p> Zheng Lin Zeyu Wang Yue Zhu Zichao Li Hao Qin Copyright (c) 2024 Zheng Lin, Zeyu Wang, Yue Zhu, Zichao Li, Hao Qin 2024-05-29 2024-05-29 3 3 27 33 10.5281/zenodo.11516191