A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing Images

This article addresses the scarcity of labeled data in multitemporal remote sensing image analysis, and especially in the context of Chlorophyll-a (Chl-a) estimation for inland water quality assessment. We propose a multitask CNN architecture that can exploit unlabeled satellite imagery and that can be generalized to other multitemporal remote sensing image analysis contexts where the target parameter exhibits seasonal fluctuations. Specifically, Chl-a estimation is set as the main task, and an unlabeled sample’s month classification is set as an auxiliary network task. The proposed approach is validated with multitemporal/spectral Sentinel-2 images of Lake Balik in Turkey using in situ measurements acquired during 2017–2019. We show that harnessing unlabeled data through multitask learning improves water quality estimation performance.

WEB DDoS Attack Detection Method Based on Semisupervised Learning

Since the services on the Internet are becoming increasingly abundant, all walks of life are inextricably linked with the Internet. Simultaneously, the Internet’s WEB attacks have never stopped. Relative to other common WEB attacks, WEB DDoS (distributed denial of service) will cause serious damage to the availability of the target network or system resources in a short period of time. At present, most researches are centered around machine learning-related DDoS attack detection algorithms. According to previous studies, unsupervised methods generally have a high false positive rate, while supervisory methods cannot handle large amount of network traffic data, and the performance is often limited by noise and irrelevant data. Therefore, this paper proposes a semisupervised learning detection model combining spectral clustering and random forest to detect the DDoS attack of the WEB application layer and compares it with other existing detection schemes to verify the semisupervised learning model proposed in this paper. While ensuring a low false positive rate, there is a certain improvement in the detection rate, which is more suitable for the WEB application layer DDoS attack detection.

Deep Learning-Based Detection and Diagnosis of Subarachnoid Hemorrhage

Subarachnoid hemorrhage (SAH) is one of the critical and severe neurological diseases with high morbidity and mortality. Head computed tomography (CT) is among the preferred methods for the diagnosis of SAH, which is confirmed by CT showing high-density shadow in the subarachnoid space. Analysis of these images through a deep learning-based subarachnoid hemorrhage will reduce the approximate rate of misdiagnosis in general and missed diagnosis by clinicians in particular. Deep learning-based detection of subarachnoid hemorrhage mainly includes two tasks, i.e., subarachnoid hemorrhage classification and subarachnoid hemorrhage region segmentation. However, it is difficult to effectively judge reliability of the model and classify bleeding which is based on limited predictive probability of convolutional neural network output. Moreover, deep learning-based bleeding area segmentation requires a large amount of training data to be marked in advance and the large number of network parameters makes the model training unable to reach the optimal. To resolve these problems associated with existing models, Bayesian deep learning and neural network-based hybrid model is presented in this paper to estimate uncertainty and efficiently classify subarachnoid hemorrhage. Uncertainty estimation of the proposed model helps in judging whether the model’s prediction is reliable or not. Additionally, it is used to guide clinicians to find the neglected subarachnoid hemorrhage area. In addition, a teacher-student mechanism deep learning model was designed to introduce observational uncertainty estimation for semisupervised learning of subarachnoid hemorrhage. Observation uncertainty estimation detects the uncertain bleeding areas in CT images and then selects areas with high reliability. Finally, it uses these unlabeled data for model training purposes as well.

Machine Learning Theory in the Strategic Management of Regional Risk Factors Measurement

Under the background of the state’s strong support for entrepreneurship, domestic small- and medium-sized enterprises ushered in the climax of development, but there are still crises coexisting with opportunities. According to statistics, most small- and medium-sized enterprises cannot survive the first three years of the initial stage of entrepreneurship. It can be said that risks exist all the time for enterprises. How to face the risk crisis and effectively avoid these regional risks has become an important factor for enterprises to survive for a long time. The accelerating pace of global economic integration has not only brought opportunities to enterprises but also brought challenges to the survival of enterprises. At present, there are few studies on regional risk in China and most of them are qualitative studies; there is no more specific quantitative study on risk factors. In view of this situation, this paper will study the quantitative evaluation model of regional risk factors based on machine learning. The development of this model adopts the method of support vector machine, which is a more commonly used risk assessment machine learning method. In order to better assess the risk, this paper also establishes a risk assessment index system, which classifies the factors of regional risk in detail and gives the specific evaluation method. Through the combination of modern technologies such as intelligent computing, semisupervised learning, and strategic center organization, the final model is established. After four risk prediction experiments including measuring the net profit margin of total assets of enterprise a, the data shows that the accuracy of the risk assessment model in this paper has been greatly improved compared with the traditional way and shows that the short-term prediction is higher than the long-term prediction and the overall prediction effect is relatively ideal, which can be applied to the practical management of regional risk prediction of enterprises.

Semisupervised Association Learning Based on Partial Differential Equations for Sparse Representation of Image Class Attributes

Semisupervised learning is an idea that addresses how to use a large number of unlabeled samples and a limited number of labeled samples to learn decision knowledge together. In this paper, we propose a multitask multiview semisupervised learning model based on partial differential equation random field and Hilbert independent standard probability image genus attribute model, i.e., shared semantics. In the framework of the image-like genus attribute model, data from different data sources are generated by their shared hidden space representation. Different from the traditional model, this paper uses the Hilbert independence criterion to inscribe the shared relationship of hidden expressions. Meanwhile, to exploit the correlations between labels in the label space as well, this paper uses the partial differential equation random field to inscribe the correlations between different kinds of labels in the label space and the correlations between hidden features and labels. Using the variational expectation-maximization algorithm, the whole generative process model can be inferred. To verify the effectiveness of the model, two artificial datasets and three real datasets are tested in this paper, and the experimental results verify the effectiveness of the algorithm in the paper. On the one hand, it not only improves the classification accuracy of the multiclassification problem and the multilabel problem; it also outputs the association structure between different kinds of labels and between hidden features and labels.

Metamaterial Reverse Multiple Prediction Method Based on Deep Learning

Metamaterials and their related research have had a profound impact on many fields, including optics, but designing metamaterial structures on demand is still a challenging task. In recent years, deep learning has been widely used to guide the design of metamaterials, and has achieved outstanding performance. In this work, a metamaterial structure reverse multiple prediction method based on semisupervised learning was proposed, named the partially Conditional Generative Adversarial Network (pCGAN). It could reversely predict multiple sets of metamaterial structures that can meet the needs by inputting the required target spectrum. This model could reach a mean average error (MAE) of 0.03 and showed good generality. Compared with the previous metamaterial design methods, this method could realize reverse design and multiple design at the same time, which opens up a new method for the design of new metamaterials.