In the medical research domain, limited data and high annotation costs have made efficient classification under few-shot conditions a popular research area. This paper proposes a meta-learning framework, termed MedOptNet, for few-shot medical image classification. The framework enables the use of various high-performance convex optimization models as classifiers, such as multi-class kernel support vector machines, ridge regression, and other models. End-to-end training is then implemented using dual problems and differentiation in the paper. Additionally, various regularization techniques are employed to enhance the model's generalization capabilities. Experiments on the BreakHis, ISIC2018, and Pap smear medical few-shot datasets demonstrate that the MedOptNet framework outperforms benchmark models. Moreover, the model training time is also compared to prove its effectiveness in the paper, and an ablation study is conducted to validate the effectiveness of each module.

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.

Electromigration-based deposition (EMBD) is an additive nanolithography technology for the fabrication of three-dimensional (3D) nanostructures. Key techniques for extending the capability of EMBD have been tackled experimentally including the deposition against a non-conductive surface, shape control of the as-deposited nanostructure, and continuous mass feeding. The process is based on nanofluidic mass delivery at the attogram scale from metal-filled carbon nanotubes (m@CNTs) using nanorobotic manipulation inside a transmission electron microscope. By attaching a conductive probe to the sidewall of the CNT, it has been shown that mass flow can be achieved regardless of the conductivity of the object surface. Experiments have shown the influence of heat sinks on the geometries of the deposits from EMBD. By modulating the relative position between the deposit and the heat sinks using dual probes, it has been possible to reshape the deposits. The limited mass encapsulated inside a CNT requires a frequent change of them for depositing large structures. To realize continuous feeding, a reservoir will be an excellent solution. We have observed that the copper inside the neighbor CNTs to the CNT injector can be sucked into the injector. Although the mechanism is not well understood yet, electromigration and atom-by-atom wall-passing-through may be responsible to this phenomenon. This observation enabled a new path for the design of an EMBD system As a general-purposed nanofabrication process, EMBD will enable a variety of applications such as nanorobotic arc welding and assembly, nanoelectrodes direct writing, and nanoscale metallurgy.