2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)最新文献_第4页

Candy classification using convolutional neural networks, data augmentation and transfer learning: Application and a new public dataset 使用卷积神经网络、数据增强和迁移学习的糖果分类:应用和一个新的公共数据集

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179072

Eduardo-José Villegas-Jaramillo, M. Orozco-Alzate

引用次数: 0

Surface sampling for optimal viewpoint generation 最佳视点生成的表面采样

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179043

V. Staderini, T. Glück, Philipp Schneider, R. Mecca, A. Kugi

{"title":"Surface sampling for optimal viewpoint generation","authors":"V. Staderini, T. Glück, Philipp Schneider, R. Mecca, A. Kugi","doi":"10.1109/ICPRS58416.2023.10179043","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179043","url":null,"abstract":"The automation of visual quality inspection is becoming increasingly important in manufacturing industries. Visual quality inspection aims to ensure that intermediate and/or final products meet certain quality features. However, automating quality inspection is challenging because the inspection process depends on the object geometry and the types of defects often encountered during manufacturing steps. As a result, manual inspection by pre-trained personnel is currently still used as the method of choice in most industries. Although some methods for automatic visual inspection planning have been proposed, each of them struggles to provide high-speed inspection with high resolution and complete (100%) coverage. In this paper, we propose a novel approach to automatically generate viewpoints, which is the first step in an automatic and flexible visual inspection pipeline. Our viewpoint generation algorithm consists of three main steps: (i) Poisson disk sampling on the target mesh and translation of the resulting samples to a predefined focusing distance along their corresponding normal vectors, (ii) sight ray tracing, and (iii) selection of the viewpoints by solving an integer linear programming problem. Additionally, we perform hyperparameter tuning using Bayesian optimization. Compared to the algorithms presented in the literature, our approach does not require a preprocessing step, and simulation results show that complete object surface coverage can be achieved even for objects with complex geometries. We demonstrate the performance of our method in terms of coverage by comparing simulation results directly with results from the literature.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130317655","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}

引用次数: 0

Temporal Analysis for the Identification of Extreme Rainfall Events Recorded in Uruguay Over a 30-Year Period (1991–2021) 乌拉圭30年(1991-2021)极端降雨事件识别的时间分析

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179084

Luana Frias-Telesca, Nelcy N. Atehortua-Sanchez, Fernando Pasini

{"title":"Temporal Analysis for the Identification of Extreme Rainfall Events Recorded in Uruguay Over a 30-Year Period (1991–2021)","authors":"Luana Frias-Telesca, Nelcy N. Atehortua-Sanchez, Fernando Pasini","doi":"10.1109/ICPRS58416.2023.10179084","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179084","url":null,"abstract":"Uruguay is a country susceptible to extreme events (heavy rainfall or drought) due to the large variation in rainfall. The identification of extreme events at a regional scale is essential since the impact due to climate change could become devastating and extended. Significant changes in climate trends make it difficult to predict extreme events. In this study, the variability of precipitation from 1991 to 2021 was analyzed at five meteorological stations of the National Institute of Agricultural Research (INIA). The data used are publicly available in open sources. The statistical analysis of the accumulated precipitation at each station shows that the stations of Tacuarembó and Salto Grande, located in the country's northern region, have a higher annual accumulated precipitation. Due to the nature of the precipitation records, a classical decomposition was performed to analyze the time series, revealing better results for the additive model and showing the seasonality in the data. This information is used to describe the behavior of the precipitation records with the possibility of making projections of the extreme events identified. The decomposition results revealed the presence of extreme events, such as heavy rainfall and prolonged periods of drought. For heavy rain events, the maximum rainfall values were determined for each station and the return periods were calculated using the Gumbel probability. The Salto Grande station is the station with the highest seasonal precipitation records for spring, summer and fall for a return period of 10 years.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131916129","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}

引用次数: 0

gAIt: Deep Learning Based Evaluation of Injurious Running Biomechanics Using Pose Estimation 步态:基于深度学习的基于姿态估计的有害跑步生物力学评估

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179061

Adarsh Iyer

{"title":"gAIt: Deep Learning Based Evaluation of Injurious Running Biomechanics Using Pose Estimation","authors":"Adarsh Iyer","doi":"10.1109/ICPRS58416.2023.10179061","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179061","url":null,"abstract":"Biomechanical errors in running form have increasingly been linked to the development of musculoskeletal injuries, precluding runners from the physical and mental benefits of long-distance running. Existing works on biomechanical anal-ysis of running form utilize expensive equipment and focus on understanding injury causes instead of predicting injury risk. In this paper, we present a novel dataset (available upon request) and three deep learning models for video analysis of running biomechanics using two-dimensional pose estimation. Our approach predicts scores corresponding to the severity of in-jurious biomechanical errors, enabling runners to improve their form based on these predictions. We collect training examples through web-scraping and supplemental recordings, to which we apply BlazePose, a pre-trained pose estimation model, to obtain spatiotemporal data series. We explore three deep learning models for time series analysis, of which a Residual Neural Network (which we term gAIt) performs best, and all models achieve greater accuracy than baseline K-Nearest Neighbors with Dynamic Time Warping. Our gAIt model and future work with this dataset may provide recreational runners with an accessible and accurate tool to improve their running form in order to stay injury-free.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129637399","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}

引用次数: 0

Enhancing Schizophrenia Prediction Using Class Balancing and SHAP Explainability Techniques on EEG Data 利用脑电数据的类平衡和SHAP可解释性技术增强精神分裂症预测

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179002

Javiera T. Arias, C. Astudillo

{"title":"Enhancing Schizophrenia Prediction Using Class Balancing and SHAP Explainability Techniques on EEG Data","authors":"Javiera T. Arias, C. Astudillo","doi":"10.1109/ICPRS58416.2023.10179002","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179002","url":null,"abstract":"Machine learning (ML) makes predictions or supports decision making based on data, achieving high accuracy, saving time and resources, and even running real-time analysis. However, one drawback of these models is the lack of transparency in complex models, reducing confidence in sensitive fields such as health. This paper analyzes electroencephalogram (EEG) data to predict schizophrenia in patients. Three classifiers are compared, considering Support Vector Machines(SVM), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost). Three metrics are used to measure the classification process, including accuracy (ACC), area under the curve (AUC) and F-l score (F1). XAI is incorporated into the pipeline to identify relevant features. XGBoost is the model with the best performance in predicting schizophrenia cases, reaching an ACC = 0.93, AUC = 0.93 and F1 score = 0.92, outperforming the SVM and AdaBoost algorithms. The SHAP explainability technique was applied on the XGBoost model, identifying the sex, IQ, delta T6, and delta Pz waves as the most relevant characteristics in the prediction processes. Based on the data analysis, we found that schizophrenia causes an alteration of the delta wave in an EEG, which is different to other mental illnesses. On the other hand, the study generates a specific impact by showing that XGBoost presents better results in 3 validation metrics (ACC, AUC, and F1 Score) compared to SVM and AdaBoost. It is shown that balancing classes is essential to obtain better ML predictions.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114388184","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}

引用次数: 0

Wh-AI-les: Exploring harmonized vision models robustness against distribution shift h- ai -les:探索协调视觉模型对分布转移的鲁棒性

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179035

Mehdi Mounsif, Mohamed Benabdelkrim, Marie-Anne Bauda, Yassine Motie

引用次数: 0

Automatic Subtractive Clustering Algorithm Model (ASCAM) for Blind Identification of QAM Constellations QAM星座盲识别的自动减法聚类算法模型

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179077

Thanapong Sommart, Vanisara Tuektaewskul, Prapun Suksompong

{"title":"Automatic Subtractive Clustering Algorithm Model (ASCAM) for Blind Identification of QAM Constellations","authors":"Thanapong Sommart, Vanisara Tuektaewskul, Prapun Suksompong","doi":"10.1109/ICPRS58416.2023.10179077","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179077","url":null,"abstract":"Blind System Identification (BSI) is a major pattern recognition task in many fields, including digital communication systems. Recently, many machine learning techniques have been applied to identify modulation types of signals solely by the receiver without prior knowledge of the transmission protocols. In this paper, we propose Automatic Subtractive Clustering Algorithm Model (ASCAM), a novel hybrid approach between subtractive clustering algorithm (SCA) and deep neural network for not only classifying the order of Quadrature Amplitude Modulation (QAM) from the corrupted baseband constellations, but also estimating the original symbols' locations in their constellations. For this model, a deep neural network based on parallel convolution is used in conjunction with a negative straight-through estimator to formulate this problem as a supervised task, regardless of the non-differentiability of SCA. Our simulation demonstrates that the model works well for QAMs with Rayleigh fading and additive white Gaussian noise (AWGN), and achieves better performance than other existing methods. It also generalizes its feature extraction well, as it can maintain its performance even when some symbols in the observed constellations are not present.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114566621","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}

引用次数: 0

A Zoom into Ecuadorian Politics: Manifesto Text Classification using NLP 放大到厄瓜多尔政治:宣言文本分类使用NLP

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10213340

Fernanda Barzallo, María Emilia Moscoso, Margorie Pérez, Maria Baldeon-Calisto, Danny Navarrete, Daniel Riofrío, Pablo Medina-Pérez, S. Lai-Yuen

{"title":"A Zoom into Ecuadorian Politics: Manifesto Text Classification using NLP","authors":"Fernanda Barzallo, María Emilia Moscoso, Margorie Pérez, Maria Baldeon-Calisto, Danny Navarrete, Daniel Riofrío, Pablo Medina-Pérez, S. Lai-Yuen","doi":"10.1109/ICPRS58416.2023.10213340","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10213340","url":null,"abstract":"Political science research on party manifestos helps to understand a candidate’s strategies and proposed actions during electoral campaigns. To achieve this, political scientists classify a manifesto’s sentences and quasi-sentences into seven main domains established by the Comparative Manifesto Project. However, manually coding is a time-consuming and labor-intensive task that can lead to biases. Automatically classifying manifestos has shown to produce good and reproducible annotations. In Ecuador, research on automatic manifesto analysis has been limited. Moreover, there is no large labeled Ecuadorian corpus available for training. Therefore, in this work we develop a Transformer network for automatically analyzing Ecuadorian manifestos using a cross-domain training approach. We implement a fractional factorial experimental design to determine which Transformer model, type of pre-processing operations, and Spanish text data should be used to maximize the accuracy of the classification model. The results show that the DistilBERT architecture trained with Mexico’s and Argentina´s manifestos increase the classification accuracy. Without using an Ecuadorian corpus for training, the implemented DistilBERT achieves a 44% accuracy on the Ecuadorian test set, which has a comparable performance to other models in literature trained with a Spanish corpus.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115158333","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}

引用次数: 0

UAV Remote Sensing applications and current trends in crop monitoring and diagnostics: A Systematic Literature Review 无人机遥感在作物监测和诊断中的应用及发展趋势:系统文献综述

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179038

Pabelco Zambrano, F. Calderon, Héctor Villegas, Jonathan Paillacho, Doménica Pazmiño, Miguel Realpe

{"title":"UAV Remote Sensing applications and current trends in crop monitoring and diagnostics: A Systematic Literature Review","authors":"Pabelco Zambrano, F. Calderon, Héctor Villegas, Jonathan Paillacho, Doménica Pazmiño, Miguel Realpe","doi":"10.1109/ICPRS58416.2023.10179038","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179038","url":null,"abstract":"Crop monitoring and diagnosis are crucial for efficient agricultural production, and unmanned aerial vehicle (UAV) Remote Sensing can assist in achieving this goal. This article offers an automated Systematic Literature Review (SLR) of UAV Remote Sensing for crop monitoring and diagnosis. This review analyzes the primary scientific applications and trends in this area using Deep Learning techniques to automatically select relevant articles and validate them through full reading. The SLR collected over 800 papers, of which 64 met the selection process. The articles selected by Deep Learning classifiers were successfully cataloged with high accuracy in pre-selecting articles for review. F1 scores of 93% were achieved in tests with unpublished examples for the classifier model. The review of the 64 primary studies reported a peak in UAV Remote Sensing applications in 2020, attributed to the increasing diffusion of precision farming practices with technological equipment. The UAV Remote Sensing application objectives included crop monitoring, pest and disease detection, yield prediction, and plant nutrition. Artificial Intelligence, particularly Machine Learning and Deep Learning, are widely used for UAV Remote Sensing analysis. The NDVI is the most applied vegetation index for crop condition assessment and monitoring. The proposed solution for automating the literature selection process for precision agriculture-related scientific articles can be used in other areas that require extensive literature review.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121188693","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}

引用次数: 0

Towards Human Intentions Prediction 人类意图预测

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179065

Marjorie Chalen T., Enrique Peláez, Ana Tapia

引用次数: 0