X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    MapLUR : Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images
    Association for Computing Machinery (ACM) ; 2020
    In:  ACM Transactions on Spatial Algorithms and Systems Vol. 6, No. 3 ( 2020-09-30), p. 1-24
    Details
    In: ACM Transactions on Spatial Algorithms and Systems, Association for Computing Machinery (ACM), Vol. 6, No. 3 ( 2020-09-30), p. 1-24
    Abstract: Land-use regression (LUR) models are important for the assessment of air pollution concentrations in areas without measurement stations. While many such models exist, they often use manually constructed features based on restricted, locally available data. Thus, they are typically hard to reproduce and challenging to adapt to areas beyond those they have been developed for. In this article, we advocate a paradigm shift for LUR models: We propose the D ata-driven, O pen, G lobal (DOG) paradigm that entails models based on purely data-driven approaches using only openly and globally available data. Progress within this paradigm will alleviate the need for experts to adapt models to the local characteristics of the available data sources and thus facilitate the generalizability of air pollution models to new areas on a global scale. To illustrate the feasibility of the DOG paradigm for LUR, we introduce a deep-learning model called MapLUR. It is based on a convolutional neural network architecture and is trained exclusively on globally and openly available map data without requiring manual feature engineering. We compare our model to state-of-the-art baselines like linear regression, random forests and multi-layer perceptrons using a large data set of modeled NO 2 concentrations in Central London. Our results show that MapLUR significantly outperforms these approaches even though they are provided with manually tailored features. Furthermore, we illustrate that the automatic feature extraction inherent to models based on the DOG paradigm can learn features that are readily interpretable and closely resemble those commonly used in traditional LUR approaches.
    Type of Medium: Online Resource
    ISSN: 2374-0353 , 2374-0361
    URL: Article
    DOI: 10.1145/3380973
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2020
    detail.hit.zdb_id: 2845842-4
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Online Resource
    Open Access Request
    Availability (electronic / print)
  • 2
    Online Resource
    Online Resource
    Emote-Controlled : Obtaining Implicit Viewer Feedback Through Emote-Based Sentiment Analysis on Comments of Popular Twitch.tv Channels
    Association for Computing Machinery (ACM) ; 2020
    In:  ACM Transactions on Social Computing Vol. 3, No. 2 ( 2020-06-30), p. 1-34
    Details
    In: ACM Transactions on Social Computing, Association for Computing Machinery (ACM), Vol. 3, No. 2 ( 2020-06-30), p. 1-34
    Abstract: In recent years, streaming platforms for video games have seen increasingly large interest, as so-called esports have developed into a lucrative branch of business. Like for other sports, watching esports has become a new kind of entertainment medium, which is possible due to platforms that allow gamers to live stream their gameplay, the most popular platform being Twitch.tv. On these platforms, users can comment on streams in real time and thereby express their opinion about the events in the stream. Due to the popularity of Twitch.tv, this can be a valuable source of feedback for streamers aiming to improve their reception in a gaming-oriented audience. In this work, we explore the possibility of deriving feedback for video streams on Twitch.tv by analyzing the sentiment of live text comments made by stream viewers in highly active channels. Automatic sentiment analysis on these comments is a challenging task, as one can compare the language used in Twitch.tv with that used by an audience in a stadium, shouting as loud as possible in sometimes nonorganized ways. This language is very different from common English, mixing Internet slang and gaming-related language with abbreviations, intentional and unintentional grammatical and orthographic mistakes, and emoji-like images called emotes . Classic lexicon-based sentiment analysis techniques therefore fail when applied to Twitch comments. To overcome the challenge posed by the nonstandard language, we propose two unsupervised lexicon-based approaches that make heavy use of the information encoded in emotes, as well as a weakly supervised neural network–based classifier trained on the lexicon-based outputs, which is supposed to help generalization to unknown words by use of domain-specific word embeddings. To enable better understanding of Twitch.tv comments, we analyze a large dataset of comments, uncovering specific properties of their language, and provide a smaller set of comments labeled with sentiment information by crowdsourcing. We present two case studies showing the effectiveness of our methods in generating sentiment trajectories for events live streamed on Twitch.tv that correlate well with specific topics in the given stream. This allows for a new kind of implicit real-time feedback gathering for Twitch streamers and companies producing games or streaming content on Twitch. We make our datasets and code publicly available for further research. 1
    Type of Medium: Online Resource
    ISSN: 2469-7818 , 2469-7826
    URL: Article
    DOI: 10.1145/3365523
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2020
    detail.hit.zdb_id: 2931552-9
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Online Resource
    Open Access Request
    Availability (electronic / print)
  • 3
    Online Resource
    Online Resource
    CLIP knows image aesthetics
    Frontiers Media SA ; 2022
    In:  Frontiers in Artificial Intelligence Vol. 5 ( 2022-11-25)
    Details
    In: Frontiers in Artificial Intelligence, Frontiers Media SA, Vol. 5 ( 2022-11-25)
    Abstract: Most Image Aesthetic Assessment (IAA) methods use a pretrained ImageNet classification model as a base to fine-tune. We hypothesize that content classification is not an optimal pretraining task for IAA, since the task discourages the extraction of features that are useful for IAA, e.g., composition, lighting, or style. On the other hand, we argue that the Contrastive Language-Image Pretraining (CLIP) model is a better base for IAA models, since it has been trained using natural language supervision. Due to the rich nature of language, CLIP needs to learn a broad range of image features that correlate with sentences describing the image content, composition, environments, and even subjective feelings about the image. While it has been shown that CLIP extracts features useful for content classification tasks, its suitability for tasks that require the extraction of style-based features like IAA has not yet been shown. We test our hypothesis by conducting a three-step study, investigating the usefulness of features extracted by CLIP compared to features obtained from the last layer of a comparable ImageNet classification model. In each step, we get more computationally expensive. First, we engineer natural language prompts that let CLIP assess an image's aesthetic without adjusting any weights in the model. To overcome the challenge that CLIP's prompting only is applicable to classification tasks, we propose a simple but effective strategy to convert multiple prompts to a continuous scalar as required when predicting an image's mean aesthetic score. Second, we train a linear regression on the AVA dataset using image features obtained by CLIP's image encoder. The resulting model outperforms a linear regression trained on features from an ImageNet classification model. It also shows competitive performance with fully fine-tuned networks based on ImageNet, while only training a single layer. Finally, by fine-tuning CLIP's image encoder on the AVA dataset, we show that CLIP only needs a fraction of training epochs to converge, while also performing better than a fine-tuned ImageNet model. Overall, our experiments suggest that CLIP is better suited as a base model for IAA methods than ImageNet pretrained networks.
    Type of Medium: Online Resource
    ISSN: 2624-8212
    URL: Article
    DOI: 10.3389/frai.2022.976235
    Language: Unknown
    Publisher: Frontiers Media SA
    Publication Date: 2022
    detail.hit.zdb_id: 2957496-1
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Online Resource
    Open Access Request
    Availability (electronic / print)
  • 4
    Online Resource
    Online Resource
    OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning
    Elsevier BV ; 2020
    In:  Atmospheric Environment Vol. 233 ( 2020-07), p. 117535-
    Details
    In: Atmospheric Environment, Elsevier BV, Vol. 233 ( 2020-07), p. 117535-
    Type of Medium: Online Resource
    ISSN: 1352-2310
    URL: Article
    DOI: 10.1016/j.atmosenv.2020.117535
    Language: English
    Publisher: Elsevier BV
    Publication Date: 2020
    detail.hit.zdb_id: 216368-8
    detail.hit.zdb_id: 1499889-0
    SSG: 14
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Online Resource
    Open Access Request
    Availability (electronic / print)
  • 5
    Online Resource
    Online Resource
    Climate change information tailored to the agricultural sector in Central Europe, exemplified on the region of Lower Franconia
    Springer Science and Business Media LLC ; 2023
    In:  Climatic Change Vol. 176, No. 10 ( 2023-10)
    Details
    In: Climatic Change, Springer Science and Business Media LLC, Vol. 176, No. 10 ( 2023-10)
    Abstract: There is a growing societal, economic, and political demand to translate available data on regional climate change into sector-specific, practice-oriented, and user-friendly information. The study presents a demand-driven approach to specify the impacts of regional climate change on agriculture, viticulture, and fruit and vegetable growing in Lower Franconia, southern Germany, a region with heterogeneous topography, diversified land use patterns, and intense activities in the sectors specified above. The approach is based on an ensemble of high-resolution regional climate model projections, a bias correction tool, and a large spectrum of meteorological (extreme) indicators that are crucial to the agricultural sector in Central Europe, as inferred from a stakeholder survey. For several decades, Lower Franconia represents a hotspot region of climate change with enhanced heat waves, prolonged droughts, and intermittent local flooding by heavy rainfall events. Results of the high-resolution regional climate model projections indicate an increase of hot days and tropical nights by a factor of 5 and 12, respectively, if greenhouse gas emissions continue to grow until 2100 according to the RCP8.5 emission scenario. At the same time, droughts will occur more frequently and last longer while rainfall intensity enhances. A longer growing period starting more than 40 days earlier (compared to the reference period 1970 to 1999) implies a higher risk of late frost damage for crops, fruits, grapes, and even some tree species. In contrast, the thermal prerequisites for viticulture will be satisfied across the entire region, even at higher-elevation sites. These facets of regional climate change are made accessible to users and the public via an interactive field-resolving web portal. Altogether, they gravely challenge the historically developed land use systems in Lower Franconia and require timely adaptation and mitigation strategies.
    Type of Medium: Online Resource
    ISSN: 0165-0009 , 1573-1480
    URL: Article
    DOI: 10.1007/s10584-023-03613-1
    RVK:
    RA 1000
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2023
    detail.hit.zdb_id: 751086-X
    detail.hit.zdb_id: 1477652-2
    SSG: 14
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Online Resource
    Open Access Request
    Availability (electronic / print)
  • 6
    Online Resource
    Online Resource
    Density-based weighting for imbalanced regression
    Springer Science and Business Media LLC ; 2021
    In:  Machine Learning Vol. 110, No. 8 ( 2021-08), p. 2187-2211
    Details
    In: Machine Learning, Springer Science and Business Media LLC, Vol. 110, No. 8 ( 2021-08), p. 2187-2211
    Abstract: In many real world settings, imba lanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point’s influence on the loss according to DenseWeight, giving rare data points more influence on model training compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points.
    Type of Medium: Online Resource
    ISSN: 0885-6125 , 1573-0565
    URL: Article
    DOI: 10.1007/s10994-021-06023-5
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2021
    detail.hit.zdb_id: 1475529-4
    detail.hit.zdb_id: 54638-0
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Online Resource
    Open Access Request
    Availability (electronic / print)
Nothing or not found what you are looking for? Please check your search query or use the Interlibrary Loan Search.
Close ⊗
This website uses cookies and the analysis tool Matomo. Further information can be found on the KOBV privacy pages