Pub Date : 2023-06-28DOI: 10.48550/arXiv.2306.16054
Michael Kolle, Steffen Illium, Maximilian Zorn, Jonas Nusslein, Patrick Suchostawski, Claudia Linnhoff-Popien
In the field of wildlife observation and conservation, approaches involving machine learning on audio recordings are becoming increasingly popular. Unfortunately, available datasets from this field of research are often not optimal learning material; Samples can be weakly labeled, of different lengths or come with a poor signal-to-noise ratio. In this work, we introduce a generalized approach that first relabels subsegments of MEL spectrogram representations, to achieve higher performances on the actual multi-class classification tasks. For both the binary pre-sorting and the classification, we make use of convolutional neural networks (CNN) and various data-augmentation techniques. We showcase the results of this approach on the challenging textit{ComparE 2021} dataset, with the task of classifying between different primate species sounds, and report significantly higher Accuracy and UAR scores in contrast to comparatively equipped model baselines.
{"title":"Improving Primate Sounds Classification using Binary Presorting for Deep Learning","authors":"Michael Kolle, Steffen Illium, Maximilian Zorn, Jonas Nusslein, Patrick Suchostawski, Claudia Linnhoff-Popien","doi":"10.48550/arXiv.2306.16054","DOIUrl":"https://doi.org/10.48550/arXiv.2306.16054","url":null,"abstract":"In the field of wildlife observation and conservation, approaches involving machine learning on audio recordings are becoming increasingly popular. Unfortunately, available datasets from this field of research are often not optimal learning material; Samples can be weakly labeled, of different lengths or come with a poor signal-to-noise ratio. In this work, we introduce a generalized approach that first relabels subsegments of MEL spectrogram representations, to achieve higher performances on the actual multi-class classification tasks. For both the binary pre-sorting and the classification, we make use of convolutional neural networks (CNN) and various data-augmentation techniques. We showcase the results of this approach on the challenging textit{ComparE 2021} dataset, with the task of classifying between different primate species sounds, and report significantly higher Accuracy and UAR scores in contrast to comparatively equipped model baselines.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"29 1","pages":"19-34"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86999976","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 : 2023-06-17DOI: 10.48550/arXiv.2307.05256
Nouran Habib, Yunsu Cho, Abhishek Buragohain, A. Rausch
One of the many Autonomous Systems (ASs), such as autonomous driving cars, performs various safety-critical functions. Many of these autonomous systems take advantage of Artificial Intelligence (AI) techniques to perceive their environment. But these perceiving components could not be formally verified, since, the accuracy of such AI-based components has a high dependency on the quality of training data. So Machine learning (ML) based anomaly detection, a technique to identify data that does not belong to the training data could be used as a safety measuring indicator during the development and operational time of such AI-based components. Adversarial learning, a sub-field of machine learning has proven its ability to detect anomalies in images and videos with impressive results on simple data sets. Therefore, in this work, we investigate and provide insight into the performance of such techniques on a highly complex driving scenes dataset called Berkeley DeepDrive.
{"title":"Towards exploring adversarial learning for anomaly detection in complex driving scenes","authors":"Nouran Habib, Yunsu Cho, Abhishek Buragohain, A. Rausch","doi":"10.48550/arXiv.2307.05256","DOIUrl":"https://doi.org/10.48550/arXiv.2307.05256","url":null,"abstract":"One of the many Autonomous Systems (ASs), such as autonomous driving cars, performs various safety-critical functions. Many of these autonomous systems take advantage of Artificial Intelligence (AI) techniques to perceive their environment. But these perceiving components could not be formally verified, since, the accuracy of such AI-based components has a high dependency on the quality of training data. So Machine learning (ML) based anomaly detection, a technique to identify data that does not belong to the training data could be used as a safety measuring indicator during the development and operational time of such AI-based components. Adversarial learning, a sub-field of machine learning has proven its ability to detect anomalies in images and videos with impressive results on simple data sets. Therefore, in this work, we investigate and provide insight into the performance of such techniques on a highly complex driving scenes dataset called Berkeley DeepDrive.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"67 1","pages":"35-55"},"PeriodicalIF":0.0,"publicationDate":"2023-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82852584","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 : 2023-01-01DOI: 10.1007/978-3-031-39059-3_26
M. Rezaei, Nasseh Tabrizi
{"title":"A Survey on Reinforcement Learning and Deep Reinforcement Learning for Recommender Systems","authors":"M. Rezaei, Nasseh Tabrizi","doi":"10.1007/978-3-031-39059-3_26","DOIUrl":"https://doi.org/10.1007/978-3-031-39059-3_26","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"108 1","pages":"385-402"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77435558","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 : 2023-01-01DOI: 10.1007/978-3-031-39059-3_10
M. A. Yazdi, Marius Politze, Benedikt Heinrichs
{"title":"Research Data Reusability with Content-Based Recommender System","authors":"M. A. Yazdi, Marius Politze, Benedikt Heinrichs","doi":"10.1007/978-3-031-39059-3_10","DOIUrl":"https://doi.org/10.1007/978-3-031-39059-3_10","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"46 1","pages":"143-156"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80897284","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 : 2023-01-01DOI: 10.1007/978-3-031-39059-3_4
Derun Xia, Y. Ko, Shivang R. Desai, A. Quyyumi
{"title":"Dynamic Prediction of Survival Status in Patients Undergoing Cardiac Catheterization Using a Joint Modeling Approach","authors":"Derun Xia, Y. Ko, Shivang R. Desai, A. Quyyumi","doi":"10.1007/978-3-031-39059-3_4","DOIUrl":"https://doi.org/10.1007/978-3-031-39059-3_4","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"13 1","pages":"56-70"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87774444","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 : 2023-01-01DOI: 10.1007/978-3-031-39059-3_27
Michael Danner, P. Huber, Muhammad Awais, Matthias Rätsch, J. Kittler
{"title":"GAN-Powered Model &Landmark-Free Reconstruction: A Versatile Approach for High-Quality 3D Facial and Object Recovery from Single Images","authors":"Michael Danner, P. Huber, Muhammad Awais, Matthias Rätsch, J. Kittler","doi":"10.1007/978-3-031-39059-3_27","DOIUrl":"https://doi.org/10.1007/978-3-031-39059-3_27","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"27 1","pages":"403-418"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81529910","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 : 2023-01-01DOI: 10.1007/978-3-031-39059-3_25
Antonio Galli, M. Gravina, S. Marrone, Carlo Sansone
{"title":"Generative Adversarial Networks for Domain Translation in Unpaired Breast DCE-MRI Datasets","authors":"Antonio Galli, M. Gravina, S. Marrone, Carlo Sansone","doi":"10.1007/978-3-031-39059-3_25","DOIUrl":"https://doi.org/10.1007/978-3-031-39059-3_25","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"11 1","pages":"370-384"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74291899","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：