Pub Date : 2021-01-01DOI: 10.5220/0010543000290037
Jaakko Tervonen, T. Sormunen, Arttu Lämsä, Johannes Peltola, Heidi Kananen, Sari Järvinen
The decision to read an article in online news media or social networks is often based on the headline, and thus writing effective headlines is an important but difficult task for the journalists and content creators. Even defining an effective headline is a challenge, since the objective is to avoid click-bait headlines and be sure that the article contents fulfill the expectations set by the headline. Once defined and measured, headline effectiveness can be used for content filtering or recommending articles with effective headlines. In this paper, a metric based on received clicks and reading time is proposed to classify news media content into four classes describing headline effectiveness. A deep neural network model using the Bidirectional Encoder Representations from Transformers (BERT) is employed to classify the headlines into the four classes, and its performance is compared to that of journalists. The proposed model achieves an accuracy of 59% on the four-class classification, and 72-78% on corresponding binary classification tasks. The model outperforms the journalists being almost twice as accurate on a random sample of headlines.
{"title":"Predicting Headline Effectiveness in Online News Media using Transfer Learning with BERT","authors":"Jaakko Tervonen, T. Sormunen, Arttu Lämsä, Johannes Peltola, Heidi Kananen, Sari Järvinen","doi":"10.5220/0010543000290037","DOIUrl":"https://doi.org/10.5220/0010543000290037","url":null,"abstract":"The decision to read an article in online news media or social networks is often based on the headline, and thus writing effective headlines is an important but difficult task for the journalists and content creators. Even defining an effective headline is a challenge, since the objective is to avoid click-bait headlines and be sure that the article contents fulfill the expectations set by the headline. Once defined and measured, headline effectiveness can be used for content filtering or recommending articles with effective headlines. In this paper, a metric based on received clicks and reading time is proposed to classify news media content into four classes describing headline effectiveness. A deep neural network model using the Bidirectional Encoder Representations from Transformers (BERT) is employed to classify the headlines into the four classes, and its performance is compared to that of journalists. The proposed model achieves an accuracy of 59% on the four-class classification, and 72-78% on corresponding binary classification tasks. The model outperforms the journalists being almost twice as accurate on a random sample of headlines.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"16 1","pages":"29-37"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73613078","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 : 2021-01-01DOI: 10.5220/0010577901770184
Yulong Wang, Xiaohui Hu, Zheshu Jia
To solve the problem of low model accuracy under noisy data sets, a filtered weighted correction training method is proposed. This method uses the idea of model fine-tuning to adjust and correct the trained deep neural network model using filtered data, which has high portability. In the data filtering process, the noise label filtering algorithm, which is based on the random threshold in the double interval, reduces the dependence on artificially set parameters, increases the reliability of the random threshold, and improves the filtering accuracy and the recall rate of clean samples. In the calibration process, to deal with sample imbalance, different types of samples are weighted to improve the effectiveness of the model. Experimental results show that the propose method can improve the F1 value of deep neural network model.
{"title":"Filtered Weighted Correction Training Method for Data with Noise Label","authors":"Yulong Wang, Xiaohui Hu, Zheshu Jia","doi":"10.5220/0010577901770184","DOIUrl":"https://doi.org/10.5220/0010577901770184","url":null,"abstract":"To solve the problem of low model accuracy under noisy data sets, a filtered weighted correction training method is proposed. This method uses the idea of model fine-tuning to adjust and correct the trained deep neural network model using filtered data, which has high portability. In the data filtering process, the noise label filtering algorithm, which is based on the random threshold in the double interval, reduces the dependence on artificially set parameters, increases the reliability of the random threshold, and improves the filtering accuracy and the recall rate of clean samples. In the calibration process, to deal with sample imbalance, different types of samples are weighted to improve the effectiveness of the model. Experimental results show that the propose method can improve the F1 value of deep neural network model.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"85 1","pages":"177-184"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80443885","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 : 2021-01-01DOI: 10.5220/0010515700930100
Silvestre Malta, Pedro Pinto, M. Fernández-Veiga
{"title":"Using Syntactic Similarity to Shorten the Training Time of Deep Learning Models using Time Series Datasets: A Case Study","authors":"Silvestre Malta, Pedro Pinto, M. Fernández-Veiga","doi":"10.5220/0010515700930100","DOIUrl":"https://doi.org/10.5220/0010515700930100","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"1 1","pages":"93-100"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82891589","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 : 2021-01-01DOI: 10.5220/0010575901640169
Constantin Rieder, M. Germann, Samuel Mezger, K. Scherer
In the present work a new approach for the concept-neutral access to information (in particular visual kind) is compiled. In contrast to language-neutral access, concept-neutral access does not require the need to know precise names or IDs of components. Language-neutral systems usually work with language-neutral metadata, such as IDs (unique terms) for components. Access to information is therefore significantly facilitated for the user in term-neutral access without required knowledge of such IDs. The AI models responsible for recognition transparently visualize the decisions and they evaluate the recognition with quality criteria to be developed (confidence). To the applicants’ knowledge, this has not yet been used in an industrial setting. The use of performant models in a mobile, low-energy environment is also novel and not yet established in an industrial setting.
{"title":"Approaches towards Resource-saving and Explainability/Transparency of Deep-learning-based Image Classification in Industrial Applications","authors":"Constantin Rieder, M. Germann, Samuel Mezger, K. Scherer","doi":"10.5220/0010575901640169","DOIUrl":"https://doi.org/10.5220/0010575901640169","url":null,"abstract":"In the present work a new approach for the concept-neutral access to information (in particular visual kind) is compiled. In contrast to language-neutral access, concept-neutral access does not require the need to know precise names or IDs of components. Language-neutral systems usually work with language-neutral metadata, such as IDs (unique terms) for components. Access to information is therefore significantly facilitated for the user in term-neutral access without required knowledge of such IDs. The AI models responsible for recognition transparently visualize the decisions and they evaluate the recognition with quality criteria to be developed (confidence). To the applicants’ knowledge, this has not yet been used in an industrial setting. The use of performant models in a mobile, low-energy environment is also novel and not yet established in an industrial setting.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"216 1","pages":"164-169"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79629448","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 : 2021-01-01DOI: 10.5220/0010549401320139
Silvan Mertes, F. Lingenfelser, Thomas Kiderle, Michael Dietz, Lama Diab, E. André
The ongoing rise of Generative Adversarial Networks is opening the possibility to create highly-realistic, natural looking images in various fields of application. One particular example is the generation of emotional human face images that can be applied to diverse use-cases such as automated avatar generation. However, most conditional approaches to create such emotional faces are addressing categorical emotional states, making smooth transitions between emotions difficult. In this work, we explore the possibilities of label interpolation in order to enhance a network that was trained on categorical emotions with the ability to generate face images that show emotions located in a continuous valence-arousal space.
{"title":"Continuous Emotions: Exploring Label Interpolation in Conditional Generative Adversarial Networks for Face Generation","authors":"Silvan Mertes, F. Lingenfelser, Thomas Kiderle, Michael Dietz, Lama Diab, E. André","doi":"10.5220/0010549401320139","DOIUrl":"https://doi.org/10.5220/0010549401320139","url":null,"abstract":"The ongoing rise of Generative Adversarial Networks is opening the possibility to create highly-realistic, natural looking images in various fields of application. One particular example is the generation of emotional human face images that can be applied to diverse use-cases such as automated avatar generation. However, most conditional approaches to create such emotional faces are addressing categorical emotional states, making smooth transitions between emotions difficult. In this work, we explore the possibilities of label interpolation in order to enhance a network that was trained on categorical emotions with the ability to generate face images that show emotions located in a continuous valence-arousal space.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"2 1","pages":"132-139"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90187630","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 : 2021-01-01DOI: 10.5220/0010551500380047
S. Scherer, Robin Schön, K. Ludwig, R. Lienhart
: This paper deals with the problem of semantic image segmentation of street scenes at night, as the recent advances in semantic image segmentation are mainly related to daytime images. We propose a method to extend the learned domain of daytime images to nighttime images based on an extended version of the CycleGAN framework and its integration into a self-supervised learning framework. The aim of the method is to reduce the cost of human annotation of night images by robustly transferring images from day to night and training the segmentation network to make consistent predictions in both domains, allowing the usage of completely unlabelled images in training. Experiments show that our approach significantly improves the performance on nighttime images while keeping the performance on daytime images stable. Furthermore, our method can be applied to many other problem formulations and is not specifically designed for semantic segmentation.
{"title":"Unsupervised Domain Extension for Nighttime Semantic Segmentation in Urban Scenes","authors":"S. Scherer, Robin Schön, K. Ludwig, R. Lienhart","doi":"10.5220/0010551500380047","DOIUrl":"https://doi.org/10.5220/0010551500380047","url":null,"abstract":": This paper deals with the problem of semantic image segmentation of street scenes at night, as the recent advances in semantic image segmentation are mainly related to daytime images. We propose a method to extend the learned domain of daytime images to nighttime images based on an extended version of the CycleGAN framework and its integration into a self-supervised learning framework. The aim of the method is to reduce the cost of human annotation of night images by robustly transferring images from day to night and training the segmentation network to make consistent predictions in both domains, allowing the usage of completely unlabelled images in training. Experiments show that our approach significantly improves the performance on nighttime images while keeping the performance on daytime images stable. Furthermore, our method can be applied to many other problem formulations and is not specifically designed for semantic segmentation.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"83 1","pages":"38-47"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78424501","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 : 2021-01-01DOI: 10.5220/0010577801700176
Yulong Wang, Jingwang Tang, Zheshu Jia
With the Automatic Identification System installed on more and more ships, people can collect a large number of ship-running data, and the relevant maritime departments and shipping companies can also monitor the running status of ships in real-time and schedule at any time. However, it is challenging to compress a large number of ship trajectory data so as to reduce redundant information and save storage space. The existing trajectory compression algorithms manage to find proper thresholds to achieve better compression effect, which is labor-intensive. We propose a new trajectory compression algorithm which utilizes Convolutional Neural Network to perform points classification, and then obtain a compressed trajectory by removing redundant points according to points classification results, and finally reduce the compression error. Our approach does not need to set the threshold manually. Experiments show that our approach outperforms conventional trajectory compression algorithms in terms of average compression error and fitting degree under the same compression rate, and has certain advantages in time efficiency.
{"title":"TC-CNN: Trajectory Compression based on Convolutional Neural Network","authors":"Yulong Wang, Jingwang Tang, Zheshu Jia","doi":"10.5220/0010577801700176","DOIUrl":"https://doi.org/10.5220/0010577801700176","url":null,"abstract":"With the Automatic Identification System installed on more and more ships, people can collect a large number of ship-running data, and the relevant maritime departments and shipping companies can also monitor the running status of ships in real-time and schedule at any time. However, it is challenging to compress a large number of ship trajectory data so as to reduce redundant information and save storage space. The existing trajectory compression algorithms manage to find proper thresholds to achieve better compression effect, which is labor-intensive. We propose a new trajectory compression algorithm which utilizes Convolutional Neural Network to perform points classification, and then obtain a compressed trajectory by removing redundant points according to points classification results, and finally reduce the compression error. Our approach does not need to set the threshold manually. Experiments show that our approach outperforms conventional trajectory compression algorithms in terms of average compression error and fitting degree under the same compression rate, and has certain advantages in time efficiency.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"2 1","pages":"170-176"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88421412","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 : 2021-01-01DOI: 10.5220/0010517001010108
Athanasios G. Ouzounis, George K. Sidiropoulos, G. Papakostas, I. Sarafis, Andreas Stamkos, George Solakis
One of the main problems in the final stage of the production line of ornamental stone tiles is the process of quality control and product classification. Successful classification of natural stone tiles based on their aesthetical value can raise profitability. Machine learning is a technology with the capability to fulfil this task with a higher speed than conventional human expert based methods. This paper examines the performance of 15 convolutional neural networks in sorting dolomitic stone tiles as far as models’ accuracy and interpretability are concerned. For the first time, these two performance indices of deep learning models are studied massively for the industrial application of machine vision based marbles sorting. The experiments revealed that the examined convolutional neural networks are able to predict the quality of the marble tiles in an industrial environment accurately in an interpretable way. Furthermore, the DenseNet201 model showed the best accuracy of 83.24%, a performance, which is supported by the consideration of the appropriate quality patterns from the marble tiles’ surface.
{"title":"Interpretable Deep Learning for Marble Tiles Sorting","authors":"Athanasios G. Ouzounis, George K. Sidiropoulos, G. Papakostas, I. Sarafis, Andreas Stamkos, George Solakis","doi":"10.5220/0010517001010108","DOIUrl":"https://doi.org/10.5220/0010517001010108","url":null,"abstract":"One of the main problems in the final stage of the production line of ornamental stone tiles is the process of quality control and product classification. Successful classification of natural stone tiles based on their aesthetical value can raise profitability. Machine learning is a technology with the capability to fulfil this task with a higher speed than conventional human expert based methods. This paper examines the performance of 15 convolutional neural networks in sorting dolomitic stone tiles as far as models’ accuracy and interpretability are concerned. For the first time, these two performance indices of deep learning models are studied massively for the industrial application of machine vision based marbles sorting. The experiments revealed that the examined convolutional neural networks are able to predict the quality of the marble tiles in an industrial environment accurately in an interpretable way. Furthermore, the DenseNet201 model showed the best accuracy of 83.24%, a performance, which is supported by the consideration of the appropriate quality patterns from the marble tiles’ surface.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"54 1","pages":"101-108"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79639049","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 : 2021-01-01DOI: 10.5220/0010506500870092
R. Bryce, R. Ueno, C. McDonald, D. Calitoiu
Identifying postal codes with the highest recruiting potential corresponding to the desired profile for a military occupation can be achieved by using the demographics of the population living in that postal code and the location of both the successful and unsuccessful applicants. Selecting N individuals with the highest probability to be enrolled from a population living in untapped postal codes can be done by ranking the postal codes using a machine learning predictive model. Three such models are presented in this paper: a logistic regression, a multi-layer perceptron and a deep neural network. The key contribution of this paper is an algorithm that combines these models, benefiting from the performance of each of them, producing a desired selection of postal codes. This selection can be converted into N prospects living in these areas. A dataset consisting of the applications to the Canadian Armed Forces (CAF) is used to illustrate the methodology proposed.
{"title":"Tailored Military Recruitment through Machine Learning Algorithms","authors":"R. Bryce, R. Ueno, C. McDonald, D. Calitoiu","doi":"10.5220/0010506500870092","DOIUrl":"https://doi.org/10.5220/0010506500870092","url":null,"abstract":"Identifying postal codes with the highest recruiting potential corresponding to the desired profile for a military occupation can be achieved by using the demographics of the population living in that postal code and the location of both the successful and unsuccessful applicants. Selecting N individuals with the highest probability to be enrolled from a population living in untapped postal codes can be done by ranking the postal codes using a machine learning predictive model. Three such models are presented in this paper: a logistic regression, a multi-layer perceptron and a deep neural network. The key contribution of this paper is an algorithm that combines these models, benefiting from the performance of each of them, producing a desired selection of postal codes. This selection can be converted into N prospects living in these areas. A dataset consisting of the applications to the Canadian Armed Forces (CAF) is used to illustrate the methodology proposed.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"72 1","pages":"87-92"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88507419","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 : 2021-01-01DOI: 10.5220/0010615501910197
M. H. Talukder, Shuhei Ota, M. Takanokura, N. Ishii
Crack detection is an issue of significant interest in ensuring the safety of buildings. Conventionally, a maintenance engineer performs crack detection manually, which is laborious and time-consuming. Therefore, a systematic crack detection method is required. Among the existing methods, convolutional neural networks (CNNs) are more effective; however, they often fail in the case of brick walls. There are several types of bricks and some may appear to have cracks owing to their structure. Additionally, the joining points of bricks may appear as cracks. It is theorized that if sub-datasets are generated based on the image attributes, and a proper sub-dataset is selected by matching the test image with the sub-datasets, then the performance of the CNN can be improved. In this study, a method consisting of sub-dataset generation and matching is proposed to improve the crack detection in brick walls. CNN learning is conducted with each sub-dataset, and crack detection is performed using a proper learned CNN that is selected by matching the test images with the images in the sub-datasets. Four performance metrics, namely, precision, recall, Fmeasure, and accuracy, are used for performance evaluation. The numerical experiments show that the proposed method improves the crack detection in brick walls.
{"title":"Sub-dataset Generation and Matching for Crack Detection on Brick Walls using Convolutional Neural Networks","authors":"M. H. Talukder, Shuhei Ota, M. Takanokura, N. Ishii","doi":"10.5220/0010615501910197","DOIUrl":"https://doi.org/10.5220/0010615501910197","url":null,"abstract":"Crack detection is an issue of significant interest in ensuring the safety of buildings. Conventionally, a maintenance engineer performs crack detection manually, which is laborious and time-consuming. Therefore, a systematic crack detection method is required. Among the existing methods, convolutional neural networks (CNNs) are more effective; however, they often fail in the case of brick walls. There are several types of bricks and some may appear to have cracks owing to their structure. Additionally, the joining points of bricks may appear as cracks. It is theorized that if sub-datasets are generated based on the image attributes, and a proper sub-dataset is selected by matching the test image with the sub-datasets, then the performance of the CNN can be improved. In this study, a method consisting of sub-dataset generation and matching is proposed to improve the crack detection in brick walls. CNN learning is conducted with each sub-dataset, and crack detection is performed using a proper learned CNN that is selected by matching the test images with the images in the sub-datasets. Four performance metrics, namely, precision, recall, Fmeasure, and accuracy, are used for performance evaluation. The numerical experiments show that the proposed method improves the crack detection in brick walls.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"13 1","pages":"191-197"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80283617","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：