The Internet of Things (IoT) has significantly enhanced various aspects of our daily lives, including security, health, education, and energy efficiency, among others. Within the realm of IoT, image classification stands as a pivotal technique that has achieved notable success in domains such as facial recognition within security and scene recognition in transportation for traffic analysis. Nonetheless, the challenge emerges when tackling classification tasks with only limited labeled samples available for each category. Conventional machine learning techniques often struggle to attain satisfactory classification results under such circumstances. To address this issue, the concept of few-shot learning has emerged, aiming to achieve effective classification using only a small number of labeled samples. State-of-the-art few-shot learning models have introduced novel frameworks to tackle this problem. However, the inherent ambiguity and uncertainty within data often hinder the performance of classification methods. To overcome this limitation, this paper proposes the integration of fuzzy learning with few-shot learning in the context of feature extraction. The objective is to mitigate data fuzziness and enhance model performance. Leveraging a fuzzy extraction algorithm, we introduce fuzzy prototype networks and a fuzzy graph neural network with fuzzy reasoning. These frameworks are designed to analyze noisy and uncertain data, utilizing convolutional neural networks for feature extraction and applying fuzzy reasoning to capture ambiguity representations for features within each fuzzy set. The SoftMax function is then normalized to serve as a feature weight, effectively constraining the original feature vector. The effectiveness and efficiency of our proposed model are demonstrated through experimental evaluations conducted on various public datasets. The results showcase the model’s capability in addressing the challenges posed by limited labeled data and data uncertainty, thus reaffirming its potential in enhancing the performance of image classification tasks within the IoT context.

Passive optical network (PON) is regarded as a promising solution for the broadband bandwidth bottleneck problem. However, due to its passive nature, legacy PON is limited by the static power distribution, which makes it power inefficient. To address this problem, we propose QPAR [4], a Quasi-Passive and Reconfigurable node, which enables dynamic power and wavelength assignment so as to save optical power budget in PON. In this paper, we study the power gains that can be achieved in PON employing QPAR, as well as different factors that may facilitate or prevent real QPAR deployments. We conduct extensive simulations to demonstrate the merits of QPAR. Results show that QPAR can achieve high optical power saving by intelligently redistributing the unnecessary power assigned to “close” optical network units (ONUs) in the network. The saved power can either be used to connect more ONUs, or extend the network reach without increasing the optical power budget.