Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.379
Yan Xia
Although students’ test scores provide an important reference for teaching and learning, research scholars still need to objectively analyze the scores. Under the current situation where English performance of vocational education students does not achieve satisfactory results, this research uses a clustering algorithm to improve on the ant colony optimization algorithm. This ant colony clustering analysis algorithm is improved by incorporating two optimization strategies, and the test scores of vocational education students are introduced as the original data for cluster analysis. The optimal number of ant colonies is nine, when the three error values of the two ant colony algorithms are minimized. The convergence values of the three ant colony algorithms are smallest when there are 200 training cycles or when the training batch size is 1000, resulting in upgraded ant colony clustering algorithm convergence values of 0.498 and 1.523, respectively. The performance of the student evaluation model combined with the ant colony clustering optimization algorithm improved, followed by CF, FOA, and BP. KNN had the worst performance. Data mining on student performance can be done via research that can provide specialized advice on students
{"title":"Innovative Teaching Via Sustainable Vocational Education with an Improved Ant Colony Algorithm","authors":"Yan Xia","doi":"10.5573/ieiespc.2023.12.5.379","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.379","url":null,"abstract":"Although students’ test scores provide an important reference for teaching and learning, research scholars still need to objectively analyze the scores. Under the current situation where English performance of vocational education students does not achieve satisfactory results, this research uses a clustering algorithm to improve on the ant colony optimization algorithm. This ant colony clustering analysis algorithm is improved by incorporating two optimization strategies, and the test scores of vocational education students are introduced as the original data for cluster analysis. The optimal number of ant colonies is nine, when the three error values of the two ant colony algorithms are minimized. The convergence values of the three ant colony algorithms are smallest when there are 200 training cycles or when the training batch size is 1000, resulting in upgraded ant colony clustering algorithm convergence values of 0.498 and 1.523, respectively. The performance of the student evaluation model combined with the ant colony clustering optimization algorithm improved, followed by CF, FOA, and BP. KNN had the worst performance. Data mining on student performance can be done via research that can provide specialized advice on students","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136017538","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.390
Jeong-Won Ha, Jong-Ok Kim
Color constancy is the ability to recognize the inherent object color invariant to surrounding illuminants. With the development of electric bulbs, there are various illuminant environments. It is an important process for image signal processing pipelines and has been studied for a long time. Most studies focus on spatial information of a single image. Several studies recently proposed the use of temporal features of high-speed video. Because light bulbs are supplied by AC (alternative current) power, the intensity varies sinusoidally with time, which can be captured with a high-speed camera. The temporal features of periodic variation were used for several color constancy studies. They showed the usefulness of temporal features. This review introduces various color constancy methods in spatial and temporal domains and compares the accuracy of illuminant estimation.
{"title":"Review of Spatial and Temporal Color Constancy","authors":"Jeong-Won Ha, Jong-Ok Kim","doi":"10.5573/ieiespc.2023.12.5.390","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.390","url":null,"abstract":"Color constancy is the ability to recognize the inherent object color invariant to surrounding illuminants. With the development of electric bulbs, there are various illuminant environments. It is an important process for image signal processing pipelines and has been studied for a long time. Most studies focus on spatial information of a single image. Several studies recently proposed the use of temporal features of high-speed video. Because light bulbs are supplied by AC (alternative current) power, the intensity varies sinusoidally with time, which can be captured with a high-speed camera. The temporal features of periodic variation were used for several color constancy studies. They showed the usefulness of temporal features. This review introduces various color constancy methods in spatial and temporal domains and compares the accuracy of illuminant estimation.","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"25 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136017539","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.419
Ying Cheng
The continuous progress of modern science and technology has led to comprehensive innovations in education, and the use of information technology for teaching has become the mainstream in the current education field. For children’s preschool language education, the application of a visual question answering (VQA) system has gradually become a new development power. This research uses a Recurrent Neural Network and a VGGNet-16 network to extract features from text and images, respectively, and applies a Hierarchical Joint Attention (HJA) model to the whole VQA system. Experiment results demonstrate that the HJA model reaches the target accuracy after 125 iterations, and convergence performance is good. When using the VQAv1 dataset, accuracy can stabilize at 88% after 18 iterations, and when using the VQAv2 dataset, the highest and lowest overall accuracy rates are 77% and 72%, respectively. The three question types (Num, Y/N, and Other) are answered with high accuracy when using the chosen preschool language education database for children, providing accuracy rates of 90%, 94%, and 91%, respectively. This new reference technique offers a new method for maximization of a VQA system, and significantly raises the preschool language education level of the children.
{"title":"Application of a Neural Network-based Visual Question Answering System in Preschool Language Education","authors":"Ying Cheng","doi":"10.5573/ieiespc.2023.12.5.419","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.419","url":null,"abstract":"The continuous progress of modern science and technology has led to comprehensive innovations in education, and the use of information technology for teaching has become the mainstream in the current education field. For children’s preschool language education, the application of a visual question answering (VQA) system has gradually become a new development power. This research uses a Recurrent Neural Network and a VGGNet-16 network to extract features from text and images, respectively, and applies a Hierarchical Joint Attention (HJA) model to the whole VQA system. Experiment results demonstrate that the HJA model reaches the target accuracy after 125 iterations, and convergence performance is good. When using the VQAv1 dataset, accuracy can stabilize at 88% after 18 iterations, and when using the VQAv2 dataset, the highest and lowest overall accuracy rates are 77% and 72%, respectively. The three question types (Num, Y/N, and Other) are answered with high accuracy when using the chosen preschool language education database for children, providing accuracy rates of 90%, 94%, and 91%, respectively. This new reference technique offers a new method for maximization of a VQA system, and significantly raises the preschool language education level of the children.","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136018008","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.448
Nisha C. Rani, N. Amuthan
{"title":"Design and Implement a Quasi-resonant Cuk Converter for Photovoltaic Applications","authors":"Nisha C. Rani, N. Amuthan","doi":"10.5573/ieiespc.2023.12.5.448","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.448","url":null,"abstract":"","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136017875","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.441
Dinh Tinh Nguyen
This paper proposes a solution to generate sector beam patterns for a sparse cylindrical sonar array (SCSA) based on construction of a mathematical expression and analysis of simulation results. With the proposed solution, the width and position of the sector beam pattern can be changed according to the number and positions of active columns in the array. The validation and effectiveness of the proposed solution are demonstrated with simulation results of sector beam patterns from different sector angles.
{"title":"Generating Sector Beam Patterns in Sparse Cylindrical Sonar Arrays","authors":"Dinh Tinh Nguyen","doi":"10.5573/ieiespc.2023.12.5.441","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.441","url":null,"abstract":"This paper proposes a solution to generate sector beam patterns for a sparse cylindrical sonar array (SCSA) based on construction of a mathematical expression and analysis of simulation results. With the proposed solution, the width and position of the sector beam pattern can be changed according to the number and positions of active columns in the array. The validation and effectiveness of the proposed solution are demonstrated with simulation results of sector beam patterns from different sector angles.","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"25 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136017541","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.404
Jingjing Yang
In order to improve accuracy in the prediction of college students" performance, a collection of students" online learning behaviors is used as input for bidirectional long short-term memory with a self-attentive mechanism to build a performance prediction model. The model is compared with K-means and LadFG algorithms in simulation experiments. The results classify students" online learning behaviors into four types (stagnant, focused, catch-up, and planned) with weighted accuracy at 0.886 and a weighted F1-score of 0.882. In the ablation experiment, the prediction model before ablation produced weighted accuracy of 0.908 and a weighted F1-score of 0.904, whereas weighted accuracy after ablation was 0.834 and the weighted F1-score was 0.835.
{"title":"Accurate Prediction and Analysis of College Students\" Performance from Online Learning Behavior Data","authors":"Jingjing Yang","doi":"10.5573/ieiespc.2023.12.5.404","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.404","url":null,"abstract":"In order to improve accuracy in the prediction of college students\" performance, a collection of students\" online learning behaviors is used as input for bidirectional long short-term memory with a self-attentive mechanism to build a performance prediction model. The model is compared with K-means and LadFG algorithms in simulation experiments. The results classify students\" online learning behaviors into four types (stagnant, focused, catch-up, and planned) with weighted accuracy at 0.886 and a weighted F1-score of 0.882. In the ablation experiment, the prediction model before ablation produced weighted accuracy of 0.908 and a weighted F1-score of 0.904, whereas weighted accuracy after ablation was 0.834 and the weighted F1-score was 0.835.","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"39 S7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136018009","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.412
Yan Liang, Feng Pan
{"title":"Study of Automatic Piano Transcription Algorithms based on the Polyphonic Properties of Piano Audio","authors":"Yan Liang, Feng Pan","doi":"10.5573/ieiespc.2023.12.5.412","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.412","url":null,"abstract":"","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"6 3-4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136017874","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.398
Xing Su, Wei Wang
Recognizing and managing college students" classroom behavior in a timely manner is of great help in improving teaching quality and strengthening classroom management. This paper builds a model based on the You Only Look Once Version 5 Small (YOLO v5s) algorithm using deep learning to detect and identify college students" classroom behaviors. The LabelImg annotation tool was used to process the dataset images, and the labeled dataset was the input for the object detection model to recognize college students" classroom behaviors. Although the precision, recall, mean average precision (mAP), and detection speed of the YOLO v5s model were slightly lower with large classroom densities, compared to medium classroom densities, the difference was negligible. At the same time, the mAP values of the proposed model under three different intersection-over-union thresholds were higher than the single shot multibox detector and regionbased convolutional neural network models, reaching 95.8, 94.3, and 92.9. This paper proves that YOLO v5s can effectively and accurately recognize classroom behavior in real time.
及时认识和管理大学生课堂行为，对提高教学质量、加强课堂管理具有重要意义。本文基于You Only Look Once Version 5 Small (YOLO v5s)算法，利用深度学习技术构建模型，对大学生课堂行为进行检测和识别。使用LabelImg标注工具对数据集图像进行处理，标记后的数据集作为目标检测模型的输入，对大学生课堂行为进行识别。虽然在教室密度较大时，YOLO v5s模型的准确率、召回率、平均平均精度(mAP)和检测速度略低，但与中等教室密度相比，差异可以忽略不计。同时，该模型在三种不同交集-过并阈值下的mAP值均高于单次多盒检测器和基于区域的卷积神经网络模型，分别达到95.8、94.3和92.9。本文证明了YOLO v5s能够有效、准确地实时识别课堂行为。
{"title":"Recognition and Identification of College Students\" Classroom Behaviors through Deep Learning","authors":"Xing Su, Wei Wang","doi":"10.5573/ieiespc.2023.12.5.398","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.398","url":null,"abstract":"Recognizing and managing college students\" classroom behavior in a timely manner is of great help in improving teaching quality and strengthening classroom management. This paper builds a model based on the You Only Look Once Version 5 Small (YOLO v5s) algorithm using deep learning to detect and identify college students\" classroom behaviors. The LabelImg annotation tool was used to process the dataset images, and the labeled dataset was the input for the object detection model to recognize college students\" classroom behaviors. Although the precision, recall, mean average precision (mAP), and detection speed of the YOLO v5s model were slightly lower with large classroom densities, compared to medium classroom densities, the difference was negligible. At the same time, the mAP values of the proposed model under three different intersection-over-union thresholds were higher than the single shot multibox detector and regionbased convolutional neural network models, reaching 95.8, 94.3, and 92.9. This paper proves that YOLO v5s can effectively and accurately recognize classroom behavior in real time.","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136017544","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.428
Jing Li, Chun Cheng
In intelligent transportation systems, accurate license plate recognition is an important component. This paper briefly introduces the LeNet-5 model for license plate image recognition. We improved the model by introducing an inception-SE convolution module. In simulation experiments, the optimized LeNet-5 model was compared with the original LeNet-5 model and a back-propagation neural network (BPNN). The results showed that the characters after preprocessing and character segmentation were clearer than those in the original images. During training, the optimized LeNet-5 converged the fastest, reached stability after 100 iterations, and had the smallest error after stability. The overall recognition accuracy of the BPNN model for the license images was 64.3%. For the original LeNet-5 model, it was 84.0%, and for the optimized LeNet-5 model, it was 98.6%.
{"title":"An Improved LeNet-5 Convolutional Neural Network for Intelligent Recognition of License Plate Images","authors":"Jing Li, Chun Cheng","doi":"10.5573/ieiespc.2023.12.5.428","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.428","url":null,"abstract":"In intelligent transportation systems, accurate license plate recognition is an important component. This paper briefly introduces the LeNet-5 model for license plate image recognition. We improved the model by introducing an inception-SE convolution module. In simulation experiments, the optimized LeNet-5 model was compared with the original LeNet-5 model and a back-propagation neural network (BPNN). The results showed that the characters after preprocessing and character segmentation were clearer than those in the original images. During training, the optimized LeNet-5 converged the fastest, reached stability after 100 iterations, and had the smallest error after stability. The overall recognition accuracy of the BPNN model for the license images was 64.3%. For the original LeNet-5 model, it was 84.0%, and for the optimized LeNet-5 model, it was 98.6%.","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"176 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136018070","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}
Pub Date : 2023-10-31DOI: 10.5573/ieiespc.2023.12.5.369
Mingi Kim, Heegwang Kim, Chanyeong Park, Joonki Paik
In this paper, we present a light-weight deep neural network based on an efficiently scaled YOLOv4 model for detecting small objects in drone images. Since drone-captured images mainly contain small objects, we modified the YOLOv4 model by eliminating the head layer responsible for detecting large objects. This modification significantly reduced the model
{"title":"Light-weight Deep Neural Network for Small Vehicle Detection using Model-scale YOLOv4","authors":"Mingi Kim, Heegwang Kim, Chanyeong Park, Joonki Paik","doi":"10.5573/ieiespc.2023.12.5.369","DOIUrl":"https://doi.org/10.5573/ieiespc.2023.12.5.369","url":null,"abstract":"In this paper, we present a light-weight deep neural network based on an efficiently scaled YOLOv4 model for detecting small objects in drone images. Since drone-captured images mainly contain small objects, we modified the YOLOv4 model by eliminating the head layer responsible for detecting large objects. This modification significantly reduced the model","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"16 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136018071","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：