Intelligent simplification of river networks is an important part in map generalisation. Traditional rule-based methods often have limitations, such as relying on the determination of parameters and thresholds. This p...
详细信息
Intelligent simplification of river networks is an important part in map generalisation. Traditional rule-based methods often have limitations, such as relying on the determination of parameters and thresholds. This paper describes the utilisation of the adaptive characteristics and powerful learning and representation capabilities of the variational autoencoder model to achieve intelligent simplification of river networks. The original river network data was sampled considering the characteristics of river networks, such as topological relationships, primary-secondary relationships and river bend curvatures. The sampled data was rasterised and input into the Encoder module. The Encoder extracted features from the images and mapped them to the latent space. Finally, the Decoder decoded the samples, mapped the latent variables back to the dimensions and distributions of the original data, and reconstructed the data as close as possible to the inputs and the river network based on the target scale. The experimental results showed that compared with the classical Douglas-Peucker, Wang-M & uuml;ller, and Visvalingam-Whyatt algorithms, this method was superior in terms of preserving the overall structure, position, shape, and local morphology of the simplified river network.
Dataset drift is a common challenge in machine learning, especially for models trained on unstructured data, such as images. In this article, we propose a new approach for the detection of data drift in black-box mode...
详细信息
Dataset drift is a common challenge in machine learning, especially for models trained on unstructured data, such as images. In this article, we propose a new approach for the detection of data drift in black-box models, which is based on Hellinger distance and feature extraction methods. The proposed approach is aimed at detecting data drift without knowing the architecture of the model to monitor, the dataset on which it was trained, or both. The article analyzes three different use cases to evaluate the effectiveness of the proposed approach, encompassing a variety of tasks including document segmentation, classification, and handwriting recognition. The use cases considered for the drift are adversarial assaults, domain shifts, and dataset biases. The experimental results show the efficacy of our drift detection approach in identifying changes in distribution under various training settings.
Machine learning has become an integral part of modern intelligent systems in all aspects of life. Membership inference attacks (MIAs), as the significant model attacks, also jeopardize the privacy of the intelligent ...
详细信息
Machine learning has become an integral part of modern intelligent systems in all aspects of life. Membership inference attacks (MIAs), as the significant model attacks, also jeopardize the privacy of the intelligent systems. Previous works on defending MIAs concentrate on the model output perturbation or tampering with the training process. However, data and model reuse are common in intelligent systems, which results in the lack of scalability of previous defending works. This paper proposes a new privacy-preserving framework for images to transform source data into synthetic data to train models against MIAs. The synthetic data makes it easy to defend MIAs during data and model reuse to improve the scheme's scalability. The framework generates synthetic data satisfying differential privacy through the variational autoencoder model's information extraction and data generation capabilities to improve model accuracy. A noise addition mechanism with metric privacy for the latent code generated from source data is proposed, where noise is the product of Gamma-distribution and unit hyper-sphere samples. Moreover, it is proved that the synthetic data also satisfies metric privacy. The experimental evaluations demonstrate that the framework reduces MIAs' attack accuracy to about 0.5 and maintains higher utility than DP-SGD under the same setting.
In recent years, significant attention has been directed towards the development of artificial empathy within the engineering academic community. Replicating artificial empathy necessitates the capability of agents to...
详细信息
In recent years, significant attention has been directed towards the development of artificial empathy within the engineering academic community. Replicating artificial empathy necessitates the capability of agents to discern human emotions and comprehend environmental risks. Analyzing acoustic data in real environments offers a higher level of non-invasive privacy compared to video and camera data, limiting the agent's understanding to specific patterns. However, current studies are negatively affected by subjective inferences from real data, which can result in inaccurate predictions, leading to both false positives and negatives, especially when contextual data and human speech are involved. This paper work proposes the estimation of a dangerous environment in accordance with the emotional speech and additional ambient noises. In this approach we implement a variational autoencoder model in conjunction with a classifier for training the classification task. Additional regularization techniques are applied to bridge the gap between the original training data and the expected data. The classifier utilizes feature data generated by the variationalautoencoder to extract class patterns and determine whether the environment is hazardous. Emotional speech is classified as angry, sad, or scared emotions, contributing to the classification of danger, while happy, calm, and neutral emotions are considered safe. Various ambient noise types, including gunfire and broken glass, are categorized as dangerous, while real-life indoor noises like cooking, eating, and movements are considered safe.
暂无评论