Logo des Repositoriums

Auflistung nach Schlagwort "resource efficiency"

1 - 3 von 3
  • Konferenzbeitrag
    Analysis and evaluation of mobile apps with regard to resource efficiency and data volumes - Methodologies and tools
    (EnviroInfo 2022, 2022) Obergöker, Kira
    The impact of software on energy and resource consumption is receiving more and more attention. While the examination of desktop software already provides initial sresults and criteria for its evaluation, the consideration of mobile apps is not quite as advanced. This paper is a first step to get an overview of which methods and tools can be used to analyse the resource and data consumption of mobile apps and to evaluate their sustainability. First, I present the previous criteria for desktop software products. In the next step, I present an existing measurement environment for determining the data volume of mobile apps. I created simple environments to identify and test components that can be used to build new measurement environments. I evaluate and compare the measurement environments based on their results. This showed variations between the environments, but an internally equal proportionality. Finally, I used the results obtained to consider how mobile apps can be analysed in terms of their resource consumption, as well as
  • Konferenzbeitrag
    Explainable AI: Leaf-based medicinal plant classification using knowledge distillation
    (44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft, 2024) Mengisti Berihu Girmay, Samuel Obeng
    Medicinal plants are used in a variety of ways in the pharmaceutical industry in many parts of the world to obtain medicines. They are traditionally used especially in developing countries, where they provide cost-effective treatments. However, accurate identification of medicinal plants can be challenging. This study uses a deep neural network and knowledge distillation approach based on a dataset of 4,026 images of 8 species of leaf-based Ethiopian medicinal plants. Knowledge from a ResNet50 teacher model was applied to a lightweight 2-layer student model. The student model, optimized for efficiency, achieved 96.91% accuracy and came close to the 98.98% accuracy of the teacher model on unseen test data. The training was built on optimization strategies, including oversampling, data augmentation, and learning rate adjustment. To understand the model's decisions, LIME (Local Interpretable Model-agnostic Explanations) and degree Grad-CAM (Gradient-weighted Class Activation Mapping) post-hoc explanation techniques were used to highlight influential image regions that contributed to classification.
  • Textdokument
    Exploration and systematic assessment of the resource efficiency of Machine Learning
    (INFORMATIK 2021, 2021) Guldner, Achim; Kreten, Sandro; Naumann, Stefan
    Estimations of today’s energy consumption of information and communication technologies (ICT) range from 2 to 9 % of the total produced energy and forecasts for the year 2030 predict an increase up to 21 %. Even though these numbers are controversial, it cannot be denied that the consumption growth of large impact factors, like data centers, networks, consumer devices, and the production of ICT needs to be reduced. In addition to Green IT, which is primarily focused on hardware, software is increasingly seen as an energy consumer with considerable savings potential. In this paper, we take a look at software for artificial intelligence (AI) and especially machine learning (ML). We describe a method for in-depth measurement and analyses of the energy consumption and hardware usage of ML algorithms and a series of experiments where we use the method on convolutional neural networks (CNN). We also compare existing estimation methods with our own. As outlook, we propose a holistic approach along the AI life cycle and additional experiments and assessments that could show potential efficiency improvements and consumption savings in AI.