Hasil untuk "Maps"

B. Huntley, H. Birks

B. Halpern

R. Szeliski, Harry Shum

C. Scotese, W. Mckerrow

J. Wisdom, M. Holman

J. Kaas

R. Ramamoorthi, P. Hanrahan

F. Moretti

H. Aronen, I. E. Gazit, D. N. Louis et al.

C. Bregler, Jitendra Malik

Byron Thom

B. Rhoades

R. Wehrens, L. Buydens

In this age of ever-increasing data set sizes, especially in the natural sciences, visualisation becomes more and more important. Self-organizing maps have many features that make them attractive in this respect: they do not rely on distributional assumptions, can handle huge data sets with ease, and have shown their worth in a large number of applications. In this paper, we highlight the kohonen package for R, which implements self-organizing maps as well as some extensions for supervised pattern recognition and data fusion.

E. Størmer

Vladimir G. Kim, Y. Lipman, T. Funkhouser

M. White

S. Hamkins

J. Coron, Tancrède Lepoint, Mehdi Tibouchi

Vladyslav Yavtukhovskyi, Violeta Tretynyk

Introduction. Convolutional neural networks (CNNs) are a subtype of neural networks developed specifically to work with images [1]. They have achieved great success both in research and in practical applications in recent years, however, one of the major pain points when adopting them is the lack of ability to interpret what is the reasoning behind their conclusion. Because of this, various explainable artificial intelligence (XAI) methods have been developed; however, it is unclear if they show reasoning or the same aspects of reasoning of CNNs. In recent years some of the most popular methods, LIME[2], SHAP[3], and Grad-CAM [4], were evaluated using tabular data and it was showed how significantly different results are [5] or some were evaluated on a matter of trustworthiness with human evaluation on medical images [6], there is still a lack of measure of how different these methods are on image classification models. This study uses correlation and a popular segmentation measure, Intersection over Union (IoU) [7], to evaluate their differences. The purpose of the article. The aim of this work is to evaluate the level of differences between SHAP, LIME, and Grad-CAM on an image classification task. Results. In this study, we evaluated the similarity between image explanations generated by SHAP, LIME, and Grad-CAM using two different models trained for specific image classification tasks. The evaluation was performed on two datasets, with one fine tuned and one pre-trained model. The datasets were the CBIS-DDSM breast cancer dataset with fine tuned ResNet-18 model, and the Imagenet Object Classification Challenge (IOCC) with a VGG-16 pre-trained model. Our analysis revealed that while all of the methods aim to approximate feature importance, their outputs significantly differ, which makes it difficult to define the true reasoning of the model. Quantitative similarity metrics confirmed that these methods were most often independent, with less than half overlap on average. To add to that, metrics were also significantly different depending on the dataset or the model. The definition of what should be the ground truth or has the best practical use for these methods is complicated, as research contains both numerous variations of fidelity metrics and significantly varies in human-based evaluation perspectives. Future work can include evaluation of the impact of method parameters on the overlap, further investigation on the impact of the dataset and the selected model on the similarity, or quantitative comparison of the models with human-based metrics, such as comparing saliency maps with segmentation masks.

Li Zhao, Jian Chen, Jiaqi Wen et al.

Per- and polyfluoroalkyl substances (PFAS), commonly known as “forever chemicals”, are ubiquitous in surface waters and potentially threaten human health and ecosystems. Despite extensive monitoring efforts, PFAS risk in European surface waters remain poorly understood, as performing PFAS analyses in all surface waters is remarkably challenging. This study developed two machine-learning models to generate the first maps depicting the concentration levels and ecological risks of PFAS in continuous surface waters across 44 European countries, at a 2-km spatial resolution. We estimated that nearly eight thousand individuals were affected by surface waters with PFAS concentrations exceeding the European Drinking Water guideline of 100 ng/L. The prediction maps identified surface waters with high ecological risk and PFAS concentration (>100 ng/L), primarily in Germany, the Netherlands, Portugal, Spain, and Finland. Furthermore, we quantified the distance to the nearest PFAS point sources as the most critical factor (14%–19%) influencing the concentrations and ecological risks of PFAS. Importantly, we determined a threshold distance (4.1–4.9 km) from PFAS point sources, below which PFAS hazards in surface waters could be elevated. Our findings advance the understanding of spatial PFAS pollution in European surface waters and provide a guideline threshold to inform targeted regulatory measures aimed at mitigating PFAS hazards.