Engineering and Technology Journal最新文献

{"title":"Apar Mangrove Density Analysis, Pariaman City, West Sumatra","authors":"Muhammad Fajri, Y. Yonvitner, Supriyanto Supriyanto","doi":"10.47191/etj/v9i07.15","DOIUrl":"https://doi.org/10.47191/etj/v9i07.15","url":null,"abstract":"Coastal areas are very vulnerable to climate change, especially due to rising sea levels that have a major effect on coastal ecosystems, including mangrove forests. Mangroves play an important ecological and economic role, but are degraded by various factors. Indonesia, which has the largest mangrove forest in the world, faces a significant decline in mangrove forest area every year, including in West Sumatra with a damage rate of 22.67%. In the city of Pariaman, which is directly opposite the Indian Ocean, there is a Mangrove Forest Park in Desa Apar that is important for the local ecosystem. This study aims to measure the density of mangroves in Apar Village using Landsat 8 satellite images and the NDVI (Normalized Difference Vegetation Index) method. The results of the analysis showed that out of a total of 10 hectares of mangrove area, 8.88 ha had a very high density, 0.55 ha had a high density, and 0.11 ha had a medium density. This data is important for the planning of mangrove protection policies and rehabilitation strategies, as well as supporting the development of sustainable ecotourism in the region. The use of technologies such as ArcGIS in NDVI analysis enables accurate vegetation monitoring, providing a solid foundation for effective mangrove management and conservation.","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"16 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141803556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced Retrieval Augmented Generation: Multilingual Semantic Retrieval across Document Types by Finetuning Transformer Based Language Models and OCR Integration","authors":"Ismail Oubah, Dr. Selçuk Şener","doi":"10.47191/etj/v9i07.09","DOIUrl":"https://doi.org/10.47191/etj/v9i07.09","url":null,"abstract":"This study presents an advanced system for multilingual semantic retrieval of diverse document types, integrating Retrieval-Augmented Generation (RAG) with transformer-based language models and Optical Character Recognition (OCR) technologies. Addressing the challenge of creating a robust multilingual Question-Answering (QA) system, we developed a custom dataset derived from XQuAD, FQuAD, and MLQA, enhanced by synthetic data generated using OpenAI's GPT-3.5 Turbo. This ensured comprehensive, context-rich answers. The inclusion of Paddle OCR facilitated high-quality text extraction in French, English, and Spanish, though Arabic presented some difficulties. The Multilingual E5 embedding model was fine-tuned using the Multiple Negatives Ranking Loss approach, optimizing retrieval of context-question pairs. We utilized two models for text generation: MT5, fine-tuned for enhanced contextual understanding and longer answer generation, suitable for CPU-friendly uses, and LLAMA 3 8b-instruct, optimized for advanced language generation, ideal for professional and industry applications requiring extensive GPU resources. Evaluation employed metrics such as F1, EM, and BLEU scores for individual components, and the RAGAS framework for the entire system. MT5 showed promising results and excelled in context precision and relevancy, while the quantized version of LLAMA 3 led in answer correctness and similarity. This work highlights the effectiveness of our RAG system in multilingual semantic retrieval, providing a robust solution for real-world QA applications and laying the groundwork for future advancements in multilingual document processing.","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"45 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141803762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Bank Loan Approval Efficiency Using Machine Learning: An Ensemble Model Approach","authors":"Md. Rezaul Islam, Md. Shariful Islam, Sharmin Shama, Aniruddha Islam Chowdhury, Md. Masudul Hasan Lamyea","doi":"10.47191/etj/v9i07.24","DOIUrl":"https://doi.org/10.47191/etj/v9i07.24","url":null,"abstract":"Lending is a major source of income for banks, but identifying worthy borrowers who will consistently repay loans is a constant problem. From a pool of loan applicants, conventional selection procedures frequently fail to find the most qualified individuals. To make loan applications faster, we created a new system that uses machine learning to automatically find people who qualify for loans. This comprehensive analysis involves data preprocessing, effective data balancing using SMOTE, and the application of various machine learning models, including Decision Trees, Support Vector Machines, K-Nearest Neighbors, Gaussian Naive Bayes, AdaBoost, Gradient Boosting, Logistic Regression, and advanced deep learning models like recurrent neural networks, deep neural networks, and long short-term memory models. We thoroughly evaluate the models based on accuracy, recall, and F1 score. Our experimental results demonstrate that the Extra Trees model outperforms its counterparts. Furthermore, we achieve a significant 0.62% increase in accuracy over the Extra Trees model by using an ensemble voting model that combines the top three machine learning models to predict bank loan defaulters. An intuitive desktop application has been developed to enhance user engagement. Remarkably, our findings indicate that the voting-based ensemble model surpasses both current state-of-the-art methods and individual ML models, including Extra Trees, with an impressive accuracy of 87.26%. Ultimately, this innovative system promises substantial improvements and efficiency in bank loan approval processes, benefiting both financial institutions and loan applicants.","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"1 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141804826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synthesized of gallium Nitride/PSi nano thin films using 532 nm wavelength by pulsed laser deposition technique","authors":"Abeer R. Abbas, A. Alwahib, M. Fakhri, S. C. B. Gopinath, U. Hashim","doi":"10.30684/etj.2024.145816.1667","DOIUrl":"https://doi.org/10.30684/etj.2024.145816.1667","url":null,"abstract":"","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"60 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141806982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Slenderness effect on the behavior of composite RC columns under eccentric loads","authors":"Zaynab S. Mohammed, Bassman R. Muhammad, A. Resheq","doi":"10.30684/etj.2024.147078.1702","DOIUrl":"https://doi.org/10.30684/etj.2024.147078.1702","url":null,"abstract":"","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"30 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141273397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechanical and thermal performance of engineered cementitious composite concrete produced by using polyvinyl alcohol fibers","authors":"Harith AL-Masraf, Tareq S. al-Attar, Qais Freyyah","doi":"10.30684/etj.2024.146641.1691","DOIUrl":"https://doi.org/10.30684/etj.2024.146641.1691","url":null,"abstract":"of the more porous structure of (PVA-ECC), the results demonstrated that adding 2% by weight of (PVA) fiber to (PVA-ECC) dramatically lowered its thermal conductivity by 36.5% compared to traditional concrete. However, more thermal energy can be captured and concentrated at the cement paste surface with the increasing amount of (PVA) fiber, causing an increment in thermal load and negatively affecting thermal insulating efficiency. Furthermore, compressive strength results revealed an upward trend as the fiber content increased up to 1.5% of (PVA) fiber, demonstrating the maximum improvement in strength. On the other hand, the achievement of 55% of the modulus of rupture by inclusion (2%) (PVA) fiber reveals that the modulus of rupture is mainly influenced by (PVA) fiber inclusion. Finally, there is confidence that the reduced thermal conductivity, hydrophobic surface nature, and improved mechanical characteristics of (PVA-ECC) can meet the demanding standards of environmentally friendly building construction.","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"15 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141273226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing Laboratory Experiments to teach Undergraduate Engineering Students Multi-User Massive MIMO Technology for 5G Cellular Networks","authors":"M. Hosany, Surfaly Bibi Shadiihah","doi":"10.47191/etj/v9i05.06","DOIUrl":"https://doi.org/10.47191/etj/v9i05.06","url":null,"abstract":"An effective method of facilitating student learning in a laboratory environment is “practice by doing”. The study of modules related to signal-processing for digital communications requires deep mathematical and theoretical foundations but the practice goal is not really emphasized in the undergraduate curriculum at the University of Mauritius. This causes the students to lose interest in the corresponding modules resulting in high rate of failures. In this work, we propose to develop laboratory experiments with a view to bridge the gap between theoretical and practical aspects in the field of Massive Multiple-Input Multiple-Output (MIMO) systems for 5G cellular networks. Various laboratory scenarios are set up that consider a Maximum Ratio Combining (MRC) receiver in the uplink with an uncorrelated Rayleigh fading channel. Moreover, from a signal processing perspective to enhance the student’s understanding, we analyze the efficiency and error performance of Massive MIMO systems with MPSK and MQAM modulation schemes as well as perfect and imperfect channel estimates. The leading industry software package MATLAB R2022 is used to develop all laboratory experiments and the codes are elaborated in this analysis. Data collected from the experiments are used to generate spectral efficiency and error performance curves which can be used for future research. The findings underscore the significance of accounting for both scenarios and illuminate promising avenues for future research in the realm of massive MIMO education and learning. The assimilation of MATLAB® flowcharts for each MRC receiver, MPSK, and MQAM with perfect and imperfect Channel State Information (CSI) adds further depth to the study, ensuring a comprehensive understanding of the intricacies of massive MIMO systems. Ultimately, this contribution helps in the nurturing of expertise such that future generations of wireless communication pioneers can be inspired.","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"69 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140973892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechanical and Geotechnical Behaviour of Improved Sandy Clay Soil for Road Pavements in Offshore Sedimentary Basins","authors":"Monique Ange Makamyou Simo, Jérémie Madjadoumbaye, J. Minane, Leonard Nsahlai Nyuykongi, Aubain Djouatsa Donfack, Emmanuel Yamb","doi":"10.47191/etj/v9i05.07","DOIUrl":"https://doi.org/10.47191/etj/v9i05.07","url":null,"abstract":"Road projects require a lot of earthworks. Sometimes, the soil in place has an insufficient bearing capacity; hence, the need to look for soil with required specifications. When a material is too far from the construction site, its transportation costful and time spending to the project. In offshore sedimentary basins, materials mostly available are sandy clay soils. This paper focuses on the improvement of the bearing capacity of sandy clay soil for different road pavements. Two solutions were investigated: lithostabilisation of sandy clay soil with volcanic rocks and cement stabilisation at different percentage in various curing conditions. Physical, geotechnical and mechanical properties were assessed on samples. It was found that, at 25% mix with volcanic gravel, sandy clayed soils are useable for the T2-T3 subbase layer and at 35% the mix can be stabilised with cement for the T2-T3 base and T4-T5 subbase layers. 4% cement dosage is the optimum for the three pavement layers. This dosage can be reduced to 2% for the T2-T3 subbase, if the negative impacts from environmental waters are counteracted. With a close look on the respect of prescribed procedures, sandy clayed soils in offshore sedimentary basins are useable for the construction of pavement layers.","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"64 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140972288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Based Lipreading for Video Captioning","authors":"Sankalp Kala, Prof. Sridhar Ranganathan","doi":"10.47191/etj/v9i05.08","DOIUrl":"https://doi.org/10.47191/etj/v9i05.08","url":null,"abstract":"Visual speech recognition, often referred to as lipreading, has garnered significant attention in recent years due to its potential applications in various fields such as human-computer interaction, accessibility technology, and biometric security systems. This paper explores the challenges and advancements in the field of lipreading, which involves deciphering speech from visual cues, primarily movements of the lips, tongue, and teeth. Despite being an essential aspect of human communication, lipreading presents inherent difficulties, especially in noisy environments or when contextual information is limited. The McGurk effect, where conflicting audio and visual cues lead to perceptual illusions, highlights the complexity of lipreading. Human lipreading performance varies widely, with hearing-impaired individuals achieving relatively low accuracy rates. Automating lipreading using machine learning techniques has emerged as a promising solution, with potential applications ranging from silent dictation in public spaces to biometric authentication systems. Visual speech recognition methods can be broadly categorized into those that focus on mimicking words and those that model visemes, visually distinguishable phonemes. While word-based approaches are suitable for isolated word recognition, viseme-based techniques are better suited for continuous speech recognition tasks. This study proposes a novel deep learning architecture for lipreading, leveraging Conv3D layers for spatiotemporal feature extraction and bidirectional LSTM layers for sequence modelling. The proposed model demonstrates significant improvements in lipreading accuracy, outperforming traditional methods on benchmark datasets. The practical implications of automated lipreading extend beyond accessibility technology to include biometric identity verification, security surveillance, and enhanced communication aids for individuals with hearing impairments. This paper provides insights into the advancements, challenges, and future directions of visual speech recognition research, paving the way for innovative applications in diverse domains.","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"56 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140974981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the impact resistance of hybrid sandwich composite body armor through experimental analysis","authors":"W. Khalaf, M. Hamzah","doi":"10.30684/etj.2024.142961.1555","DOIUrl":"https://doi.org/10.30684/etj.2024.142961.1555","url":null,"abstract":"","PeriodicalId":507832,"journal":{"name":"Engineering and Technology Journal","volume":"112 26","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140986851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}