Auflistung nach Schlagwort "convolutional neural network"
1 - 4 von 4
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelArtificial intelligence for molecular communication(it - Information Technology: Vol. 65, No. 4-5, 2023) Bartunik, Max; Kirchner, Jens; Keszocze, OliverMolecular communication is a novel approach for data transmission between miniaturised devices, especially in contexts where electrical signals are to be avoided. The communication is based on sending molecules (or other particles) at nanoscale through a typically fluid channel instead of the “classical” approach of sending electrons over a wire. Molecular communication devices have a large potential in future medical applications as they offer an alternative to antenna-based transmission systems that may not be applicable due to size, temperature, or radiation constraints. The communication is achieved by transforming a digital signal into concentrations of molecules that represent the signal. These molecules are then detected at the other end of the communication channel and transformed back into a digital signal. Accurately modeling the transmission channel is often not possible which may be due to a lack of data or time-varying parameters of the channel (e.g., the movements of a person wearing a medical device). This makes the process of demodulating the signal (i.e., signal classification) very difficult. Many approaches for demodulation have been discussed in the literature with one particular approach having tremendous success – artificial neural networks. These artificial networks imitate the decision process in the human brain and are capable of reliably classifying even rather noisy input data. Training such a network relies on a large set of training data. As molecular communication as a technology is still in its early development phase, this data is not always readily available. In this paper, we discuss neural network-based demodulation approaches relying on synthetic simulation data based on theoretical channel models as well as works that base their network on actual measurements produced by a prototype test bed. In this work, we give a general overview over the field molecular communication, discuss the challenges in the demodulations process of transmitted signals, and present approaches to these challenges that are based on artificial neural networks.
- KonferenzbeitragDetection of snow-coverage on PV-modules with images based on CNN-techniques(EnviroInfo 2022, 2022) Hepp, Dennis; Hempelmann, Sebastian; Behrens, Grit; Friedrich, WernerThe transition from fossil fuels to renewable energy is considered as very meaningful to mitigate climate change. To integrate weather-dependent energies firmly into the power grid, a forecast of the energy yield is very important. This paper is about renewable energy generation by photovoltaic (PV) systems. The yield of PV-systems depends not only on weather conditions, but in wintertime also on the additional factor “snow cover”. The aim of this work is to detect snow cover on photovoltaic plants to support the energy yield forecast. For this purpose, images of a PV-plant with and without snow cover are used for feature extraction and then analyzed by using a convolutional neural network (CNN).
- KonferenzbeitragExplainable AI: Leaf-based medicinal plant classification using knowledge distillation(44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft, 2024) Mengisti Berihu Girmay, Samuel ObengMedicinal 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.
- KonferenzbeitragKnuckleTouch: Enabling Knuckle Gestures on Capacitive Touchscreens using Deep Learning(Mensch und Computer 2019 - Tagungsband, 2019) Schweigert, Robin; Leusmann, Jan; Hagenmayer, Simon; Weiß, Maximilian; Le, Huy Viet; Mayer, Sven; Bulling, AndreasWhile mobile devices have become essential for social communication and have paved the way for work on the go, their interactive capabilities are still limited to simple touch input. A promising enhancement for touch interaction is knuckle input but recognizing knuckle gestures robustly and accurately remains challenging. We present a method to differentiate between 17 finger and knuckle gestures based on a long short-term memory (LSTM) machine learning model. Furthermore, we introduce an open source approach that is ready-to-deploy on commodity touch-based devices. The model was trained on a new dataset that we collected in a mobile interaction study with 18 participants. We show that our method can achieve an accuracy of 86.8% on recognizing one of the 17 gestures and an accuracy of 94.6% to differentiate between finger and knuckle. In our evaluation study, we validate our models and found that the LSTM gestures recognizing archived an accuracy of 88.6%. We show that KnuckleTouch can be used to improve the input expressiveness and to provide shortcuts to frequently used functions.