Proceedings of Engineering and Technology Innovation
https://ojs.imeti.org/index.php/PETI
<p><strong><em>Proceedings of Engineering and Technology Innovation</em></strong> (PETI), ISSN 2518-833X (Online), ISSN 2413-7146 (Print), is an international, multidiscipline, open access, peer-reviewed scholarly journal, and dedicated to providing a fast publishing platform for researchers, developers, technical managers, and educators in the field of technology innovation. The officially abbreviated title is <em><strong>Proc. eng. technol. innov.</strong></em> It is published by Taiwan Association of Engineering and Technology Innovation.</p> <p>PETI is indexed by:</p> <p><span style="color: black; font-family: 'Noto Sans'; font-size: 10.5pt;"> <img style="width: 136px; height: 26px;" src="https://ojs.imeti.org/public/site/images/allen/image001.png" alt="" width="171" height="53" /> <img src="https://ojs.imeti.org/public/site/images/allen/DOAJ-small3.png" /> <img src="https://ojs.imeti.org/public/site/images/allen/ProQuest-4.png" width="74" height="35" /> <img src="https://ojs.imeti.org/public/site/images/ijeti/google6.png" alt="" /> <img src="https://ojs.imeti.org/public/site/images/ijeti/Resarch_Bible6.png" alt="" /> <img src="https://ojs.imeti.org/public/site/images/ijeti/WorldCat6.png" alt="" /> <img src="https://ojs.imeti.org/public/site/images/allen/academia-13.png" /> <img src="https://ojs.imeti.org/public/site/images/ijeti/CNKI1.png" alt="" /> <img src="https://ojs.imeti.org/public/site/images/ijeti/TOCs6.jpg" alt="" /> <img src="https://ojs.imeti.org/public/site/images/allen/Publons-22.5_.png" /> <img src="https://ojs.imeti.org/public/site/images/allen/crossref3.png" width="92" height="42" /></span></p> <p>Under evaluation of SCI(E), Compendix(EI), INSPEC, etc.</p> <p> </p>Taiwan Association of Engineering and Technology Innovationen-USProceedings of Engineering and Technology Innovation2413-7146<hr> <p style="line-height: 150%;"><span style="font-family: Times New Roman;">Submission of a manuscript implies: that the work described has not been published before that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication. Authors can retain copyright of their article with no restrictions. Also, author can post the final, peer-reviewed manuscript version (postprint) to any repository or website.</span></p> <p> </p> <p style="line-height: 150%;"><img alt="" src="/public/site/images/ijeti/cc.png"><br><span style="font-family: Times New Roman, Times, serif;">Since Oct. 01, 2015, PETI will publish new articles with Creative Commons Attribution Non-Commercial License, under </span><span style="font-family: Times New Roman, Times, serif;"><a href="https://creativecommons.org/licenses/by-nc/4.0/">The Creative Commons Attribution Non-Commercial 4.0 International (CC BY-NC 4.0) License</a>.<br>The Creative Commons Attribution Non-Commercial (CC-BY-NC) License permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes</span></p>Recognition of Ginger Seed Growth Stages Using a Two-Stage Deep Learning Approach
https://ojs.imeti.org/index.php/PETI/article/view/12701
<p>Monitoring the growth of ginger seed relies on human experts due to the lack of salient features for effective recognition. In this study, a region-based convolutional neural network (R-CNN) hybrid detector-classifier model is developed to address the natural variations in ginger sprouts, enabling automatic recognition into three growth stages. Out of 1,746 images containing 2,277 sprout instances, the model predictions revealed significant confusion between growth stages, aligning with the human perception in data annotation, as indicated by Cohen’s Kappa scores. The developed hybrid detector-classifier model achieved an 85.50% mean average precision (mAP) at 0.5 intersections over union (IoU), tested with 402 images containing 561 sprout instances, with an inference time of 0.383 seconds per image. The results confirm the potential of the hybrid model as an alternative to current manual operations. This study serves as a practical case, for extensions to other applications within plant phenotyping communities.</p>Yin-Syuen TongTou-Hong LeeKin-Sam Yen
Copyright (c) 2023 Yin-Syuen Tong, Tou-Hong Lee, Kin-Sam Yen
http://creativecommons.org/licenses/by-nc/4.0
2024-02-292024-02-2926011710.46604/peti.2023.12701A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification
https://ojs.imeti.org/index.php/PETI/article/view/13200
<p>Fake profile identification on social media platforms is essential for preserving a reliable online community. Previous studies have primarily used conventional classifiers for fake account identification on social networking sites, neglecting feature selection and class balancing to enhance performance. This study introduces a novel multistage stacked ensemble classification model to enhance fake profile detection accuracy, especially in imbalanced datasets. The model comprises three phases: feature selection, base learning, and meta-learning for classification. The novelty of the work lies in utilizing chi-squared feature-class association-based feature selection, combining stacked ensemble and cost-sensitive learning. The research findings indicate that the proposed model significantly enhances fake profile detection efficiency. Employing cost-sensitive learning enhances accuracy on the Facebook, Instagram, and Twitter spam datasets with 95%, 98.20%, and 81% precision, outperforming conventional and advanced classifiers. It is demonstrated that the proposed model has the potential to enhance the security and reliability of online social networks, compared with existing models.</p>Swetha Chikkasabbenahalli VenkateshSibi ShajiBalasubramanian Meenakshi Sundaram
Copyright (c) 2024 Swetha Chikkasabbenahalli Venkatesh, Sibi Shaji, Balasubramanian Meenakshi Sundaram
http://creativecommons.org/licenses/by-nc/4.0
2024-02-292024-02-2926183210.46604/peti.2024.13200Performance Analysis of Open Steam Power Cycle Powered by Concentrated Solar Energy
https://ojs.imeti.org/index.php/PETI/article/view/13201
<p>This study aims to develop a concentrated solar receiver designed to directly generate steam for driving a steam turbine within the steam power cycle of a carbon-free system. The solar power system consists of parabolic dishes, evaporation tanks, and a steam turbine, and the experimental setup was tested on different days, analyzing the measured parameters with the EES software. Results from the investigation indicate that, under the optimal conditions with a maximum recorded temperature and pressure of 143 ℃ and 2.5 bar, respectively, and a vaporized water mass of 100 grams, the manufactured turbine achieved a maximum isentropic efficiency of 92.48% and a power of 1.76 W. Notably, the evaporation tank and the mini steam turbine demonstrated the capability to generate steam and mechanical power, respectively, without relying on conventional energy.</p>Ayad Tareq MustafaMohammed Mahmood Hadi
Copyright (c) 2024 Ayad Tareq Mustafa, Mohammed Mahmood Hadi
http://creativecommons.org/licenses/by-nc/4.0
2024-02-292024-02-2926334410.46604/peti.2024.13201A Codebook Compression Method for Vector Quantization Algorithm
https://ojs.imeti.org/index.php/PETI/article/view/13268
<p>This study introduces a novel approach to enhance the compression ratio of the vector quantization (VQ) algorithm by specifically targeting the compression of its codebook. The VQ algorithm typically generates an index matrix and a codebook to represent compressed images. The proposed method focuses on reducing the size of the codebook, which comprises N codewords, each with elements quantized into four levels. Each 8-bit element in a codeword is compressed to 2-bits, and the encoded codeword is accompanied by the minimum value and a threshold value in the codebook. Experimental results on benchmark color images, such as baboon, airplane, Lena, and others, demonstrate a significant reduction of 62.50% in the size of the VQ codebook.</p>Abul HasnatDibyendu BarmanMd Azizul HoqueSantanu HalderDebotosh Bhattacharjee
Copyright (c) 2024 Abul Hasnat, Dibyendu Barman, Md Azizul Hoque, Santanu Halder, Debotosh Bhattacharjee
http://creativecommons.org/licenses/by-nc/4.0
2024-02-292024-02-2926455410.46604/peti.2024.13268Evolution of Vortex Structures Generated by a Rigid Flapping Wing with a Winglet in Quiescent Water
https://ojs.imeti.org/index.php/PETI/article/view/12838
<p>This study aims to the utilization of vortex structures generated through wing flapping for achieving sustainable flight, and the motivation is elicited by the phenomenon observed in natural flyers. The vortex structures in the flow field generated by a flapping rigid wing are captured using vorticity and the LAMDA2 criterion. The study investigates a comparative analysis between a wing both with and without a winglet. Moreover, the influence of flapping frequency is examined as well. For the experiments, particle image velocimetry (PIV) measurements are employed for the flow field around mechanical flapping motion in a quiescent water condition. The flapping mechanism has one-degree freedom, showing a 1:3 ratio in motion, and tested wings at 1.5 and 2.0 Hz. A “modified” vortex filamentation and fragmentation phenomenon is proposed as a significant finding in the present study, based on a comprehensive analysis of the flow field around the wing with a winglet.</p>Srikanth GoliArnab RoySubhransu RoyImil Hamda Imran
Copyright (c) 2023 Srikanth Goli, Arnab Roy, Subhransu Roy, Imil Hamda Imran
http://creativecommons.org/licenses/by-nc/4.0
2024-02-292024-02-2926557110.46604/peti.2023.12838BAT Algorithm-Based Multi-Class Crop Leaf Disease Prediction Bootstrap Model
https://ojs.imeti.org/index.php/PETI/article/view/13352
<p>In the task of identification of infected agriculture plants, the leaf-based disease identification technique is especially effective in better understand crop disease among various techniques to detect infection. Recognition of an infected leaf image from healthy images gets encumbered when the model is required to detect the type of leaf disease. This paper presents a BAT-based crop disease prediction bootstrap model (BCDPBM) that identifies the health of the leaf and performs disease prediction. The BAT algorithm in the proposed model increases the capability of the Gaussian mixture model for foreground region detection. Furthermore, in the work, the co-occurrence matrix feature and histogram feature are extracted for the training of the bootstrap model. Hence, leaf foreground detection by the BAT algorithm with the Gaussian mixture improves the feature extraction quality for bootstrap learning. The proposed model utilizes a dataset of real leaf images for conducting experiments. The results of the model are compared with different existing models across various parameters. The results show the prediction accuracy enhancement of multiclass leaf disease using the BCDPBM model.</p>Vijay ChoudharyArchana Thakur
Copyright (c) 2024 Vijay Choudhary, Archana Thakur
http://creativecommons.org/licenses/by-nc/4.0
2024-02-292024-02-2926728210.46604/peti.2024.13352