2023 Intelligent Methods, Systems, and Applications (IMSA)最新文献

{"title":"Football activities classification","authors":"Ahmed Mohamed Emam, Omar Tarek Ali, Ayman Atia","doi":"10.1109/IMSA58542.2023.10217464","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217464","url":null,"abstract":"Football, also known as soccer in some regions, is a popular sport that requires teams to score more goals than each other to win. As the sport gains more popularity, people are increasingly interested in learning its techniques. This study proposes a system that can help users learn football techniques such as juggling, inside-of-the-foot pass, and fake shot double tap (drill), and this move is divided into two parts. The system offers real-time feedback on users' actions, allowing them to learn more effectively. To achieve this, the system uses Mediapipe, an open-source library, to extract the coordinates of the human skeleton from the video recorded by the user. Besides, four classification algorithms, namely dollarpy, KNN, RFE, and SVM, to classify the actions performed by the user. If the user performs any of the specified actions correctly, they are awarded one point, and at the end of the session, they receive a report indicating how many times they performed each action. System results show that the model was able to predict the actions with high accuracy. The accuracies reached by the models used RFE, SVM, KNN, and dollarpy were 80%, 90%, 75&, and 55% respectively.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126639861","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":"End of Session (6)","authors":"","doi":"10.1109/imsa58542.2023.10217390","DOIUrl":"https://doi.org/10.1109/imsa58542.2023.10217390","url":null,"abstract":"","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125665962","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":"Understanding of gait classification using template-matching techniques","authors":"Dema Saleh, Youssef Ayman, Ayman Atia","doi":"10.1109/IMSA58542.2023.10217438","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217438","url":null,"abstract":"Gait analysis is the methodical study of movements and motion, more especially the analysis of human motion patterns, using observers’ eyes and brains in addition to equipment for observing kinematics, body mechanics, and muscle activity as a human being’s gait is deeply influential on their mobility and overall health. Measurement and interpretation in gait analysis involve the introduction and analysis of quantifiable parameters and the generation of conclusions about the participant. Thus, the field of gait analysis on 2D video files with the assistance of computer vision methods and tools is the natural direction to take. The proposed system manages to successfully differentiate between two different classes of gait Through comparison of the input and output. This is used to detect abnormal or irregular habits in a person’s gait. Gait analysis is the systematic study of movements and motion, more especially the analysis of human motion patterns, using observers’ eyes and brains in addition to equipment for observing kinematics, and body mechanics. Consequentially, Gait analysis involves a staggering amount of interconnected characteristics, making it challenging to apply due to the volume of data and relationships involved. Thus the goal is to pursue a simple analysis method that is reliant solely on an input video of a participant walking. The dataset used in this system consisted of 33 training videos, and 31 testing videos. This demanded the use of computer vision and machine learning techniques which are approached through several methods. Such methods included the use of pose detection techniques and a geometric template identifier. A simple method was used so that it does not require heavy computation to be compatible with most of the users and patients. Dollar py was the algorithm chosen to match the distance between templates using Euclidean distance matching. The obtained output indicated whether the received footage was normal or abnormal and had the confidence level of each result. These findings imply that pose estimation algorithms based on deep networks and single-camera footage are employed to measure pertinent gait parameters in people.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122288104","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":"Ensemble Machine learning for Breast Cancer Detection","authors":"Nourhan Elsabawy, Alaa Elnakeeb, Mohammed Baher, N. Elrashidy","doi":"10.1109/IMSA58542.2023.10217633","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217633","url":null,"abstract":"Breast cancer (BC) is a serious issue and the biggest global cause of death for women. Therefore, it is crucial to find BC early in order to save their lives. Models for the prognosis of some diseases have been developed using machine learning (ML), which has been shown to play a crucial role in this process. In this study, we present a model that can distinguish between cancerous and healthy BC cells in order to classify people into those who have BC and those who do not. In order to optimize the characteristics and select the best subset from them, this study leverages the feature selection (FS) phenomenon. We examine six machine learning models: the decision tree (DT), random forest (RF), KNN, support vector machine (SVM), and logistic regression (LR). In order to assess the performance Of this paper’s classification models, we calculated precision, accuracy, recall, and F1-score to assess their performance. On the dataset, both before and after applying the FS approach, the six ML models’ performance was evaluated. The experimental outcomes demonstrate that LR and SVM are equally accurate and produce the greatest results when compared to other ML models, with a 98.246% accuracy that increases to 98.83% with Fs. A voting ensemble ML model was created based on LR, SVM, and other ML techniques to attain the greatest performance. Compared to other classic ML methods, ensemble models perform better.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128274200","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":"Comparing the Effectiveness of Machine Learning and Deep Learning Techniques for Feature Envy Detection in Software Systems","authors":"Rana S. Menshawy, A. Yousef, Ashraf Salem","doi":"10.1109/IMSA58542.2023.10217458","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217458","url":null,"abstract":"Code smells are common in poorly designed software that can hinder code maintainability. Automatic detection of design flaws assists developers in identifying code smells in theirsoftware programs to avoid low-quality delivery. However, the interpretation of code smells is subjective, and existing machine learning-based detection tools are limited in their ability to capture complex semantic relationships in textual code. To address this limitation, the paper proposes a detection system that exploits machine learning and deep learning techniques and compares their effectiveness in identifying the feature envy code smell. The study applies six deep learning techniques based on code semantics features extracted from abstract syntax trees, and eleven machine learning techniques based on code structural features. The results show that both approaches are effective in detecting code smells, with Random Forest achieving exceptional performance among the machine learning classifiers.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128376909","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":"Performance Evaluation of Pre-Trained Deep Learning Models for Bird Species Identification","authors":"Kerolos Hany, Youssef Ayman, Ayman Atia","doi":"10.1109/IMSA58542.2023.10255070","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10255070","url":null,"abstract":"The goal of this work was to measure the performance of pre-trained deep-learning models for bird species identification. A flatten layer, three dense layers, two dropout layers, and an output layer with a softmax activation function were utilized in the study's CNN classification models. Precision, recall, and f1-score were some of the evaluation measures used to gauge how well the pre-trained models performed. The results show that the ResNet50v2 and Inceptionv3 models successfully identified bird species with high levels of accuracy, with ResNet50v2 achieving an accuracy of 97.32%. VGG19, on the other hand, has a comparably lower accuracy of 67.82%. These results reveal that pre-trained models have great promise to be effective tools for identifying bird species, with ResNet50v2 and Inceptionv3 providing the most promising results.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"21 1","pages":"309-314"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139359198","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":"Framework for Crack Detection using Deep Learning","authors":"Omar Atta, Ayman Atia","doi":"10.1109/IMSA58542.2023.10217751","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217751","url":null,"abstract":"This study presents an innovative hierarchical classification approach aimed at detecting and classifying various types of road cracks. The methodology consists of three main stages: image preprocessing, binary classification, and hierarchical classification. The first experiment incorporates a binary classification model based on the OLenet architecture, where after preprocessing, the model is trained and tested on the Metu and ELpv datasets, achieving impressive accuracies of 97% and 92%, respectively. In the second experiment, the method amalgamates the Road Crack and Solar Cells datasets into a diverse dataset of 4,000 images. A Convolutional Neural Network (CNN) model is trained on this combined dataset using transfer learning techniques and architectures like VGG16, VGG19, and MobileNet, where the VGG19 model demonstrates superior performance with a classification accuracy of 98.69%. The final experiment involves a Mask RCNN model trained on the Road Crack dataset with 7,048 images of 13 distinct types of road cracks, offering the unique capability to classify multiple types of cracks within a single image and outperforming traditional CNN models with an accuracy of 90.42%. This novel approach holds significant potential for effective road crack detection and classification, contributing to enhanced road maintenance and safety. Future work will expand the hierarchical classifier with more crack types and further optimize the accuracy of all models. The main contributions of this study lie in its unique methodological approach, the effective use of diverse datasets, and the successful application of transfer learning and the Mask RCNN model.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131249409","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":"Incorporating Connectivity in k-Nearest Neighbors Regression","authors":"M. Mahfouz","doi":"10.1109/IMSA58542.2023.10217502","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217502","url":null,"abstract":"The standard k-nearest neighbors’ approach to regression analysis encounters a number of problems when used on datasets with various density distributions. This paper proposes a kNNR-relative ensemble regressor based on connectivity. In each cross-validation round, the pipeline starts by clustering the input data using any partitioning algorithm. Then, a random sample of the edges is selected from each partition favoring the edges with small distances. After that, the selected edges are transformed into a dataset in which feature values represent the amount of increase or decrease in each dimension compared to the source node’s values and the label of each feature vector is the difference in the label of the source and the destination. Then a regressor is built for each cluster based on the output of the transformer. In order to predict a label for an unseen object, the nearest centroid is identified, and, k-nearest neighbors from the corresponding cluster are identified as the source nodes. Then, a vector representing the difference between the unseen object and each source node is computed and fed to the regressor model of the corresponding cluster, the output label is the predicted difference so it is added to the label of the source node. The diversity between the suggested decision model and the traditional kNN regressor, termed kNNR motivates us to include the kNNR in the suggested ensemble. The k-nearest neighbors of kNNR are also selected from the nearest cluster. The weighted average of the predicted labels offered by the base models serves as the final output label. The sample size, the number of neighbors to be used, and the number of clusters can all be fine-tuned via cross validation. The ensemble is evaluated, and the results showed that the ensemble achieved a significant increase in effectiveness compared to its base regressors and several related algorithms.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134423348","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":"Session (7)","authors":"","doi":"10.1109/imsa58542.2023.10217389","DOIUrl":"https://doi.org/10.1109/imsa58542.2023.10217389","url":null,"abstract":"","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133203770","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":"Smart Prediction of Circulatory Failure: Machine Learning for Early Detection of Patient Deterioration","authors":"Shrouk Hesham Mahmoud, Sahar Selim Soussa, Aya Mohamed Hassan, Hussin Fekry Abdelrazik, Seifeldin Mohamed Hashem, Abdelrahman Mahmoud Mari","doi":"10.1109/IMSA58542.2023.10217593","DOIUrl":"https://doi.org/10.1109/IMSA58542.2023.10217593","url":null,"abstract":"Circulatory failure, also known as shock, is a critical condition that can have serious consequences for one’s health. Early detection and timely intervention are crucial for improving patient outcomes. Machine learning (ML) models have shown promise in predicting circulatory failure based on clinical data. In our study, we examined different machine learning (ML) models to predict circulatory failure in patients who were admitted to the intensive care unit (ICU) with suspected circulatory problems. The ML model we developed used various algorithms like random forest, LG, XGB, Decision Tree, and SVM. It was trained using clinical information such as vital signs, laboratory values, and demographic data. By considering these different factors, our model aimed to accurately predict circulatory failure in critically ill patients. Furthermore, we employed feature selection techniques such as SelectKBest to identify the most informative clinical variables for prediction. Using receiver operating characteristic (ROC) curves and area under the curve (AUC) values, we evaluated the model’s performance. Our results show that machine learning models can contribute significantly to predicting circulatory failure in patients at high risk of deterioration.","PeriodicalId":110239,"journal":{"name":"2023 Intelligent Methods, Systems, and Applications (IMSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131222374","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}