Sewer networks (SNs) are susceptible to various factors that can lead to failures, resulting in economic losses and environmental pollution. Data-driven approaches based on sewage flow monitoring enhance the awareness and maintenance capabilities of SNs. However, the current research lacks early warning systems for flow anomalies. This presents a challenge for the application of supervised methods, primarily due to the scarcity of anomalous flow datasets. Even with the availability of such datasets, the effectiveness of these methods may vary due to environmental differences, since SNs are situated in diverse environments. Therefore, effectively achieving early warnings for anomalies in unlabeled flow data is a challenge that must be addressed in the field of flow monitoring. To address this challenge, we propose a detection method for effectively warning of anomalies in flow data. Since anomalies typically result in significant deviations from normal data, early warnings can be achieved by comparing the differences between current and historical data. The key to this early warning lies in establishing an adaptive threshold for detecting abnormal data changes. Our detection method employs an unsupervised bagging-based multi-anomaly detection algorithm to detect such abnormal data changes. Experiments conducted on Erhai Lake SNs flow data demonstrate that our method can predict anomalies 5-15 minutes in advance with a precision of 80.00%, a recall of 66.67%, and an F1 score of 0.73. Our approach not only achieves cost-effective and timely anomalies detection but also overcomes the challenges associated with limited dataset availability, making it applicable to various other industries.

Circulating tumor cell (CTC) detection is crucial for reducing cancer mortality and disease burden. Traditional methods rely on the physical or biological properties of CTCs and involve complex enrichment and separation processes, which are often inefficient and limited by cellular heterogeneity and detection accuracy, making them unsuitable for rapid screening. In contrast, intelligent cell recognition and classification using low-resolution microscopy images allows faster detection. Supervised learning has shown excellent performance in CTC detection; however, it heavily depends on large quantities of labeled immunofluorescence image data, which not only consumes significant expert time and resources but also increases costs, limiting its widespread applications. Furthermore, the scarcity of public datasets and the high costs of proprietary datasets further hinder detection effectiveness. Therefore, developing costeffective, personalized datasets is essential for practical application. Unsupervised methods, which perform classification without the need for manual labeling, offer promising solutions to overcome these challenges. This study adopts an unsupervised classification method that performs excellently on fungal datasets [1], integrating two-step dimensionality reduction and hybrid clustering voting for automated CTC classification. This method does not require manual labeling, achieves an accuracy of 98.2%, and has a discard rate of 25.23%, effectively distinguishing CTCs from white blood cells (WBCs). By reducing the dependence on manually labeled data, this approach lowers the cost and complexity of creating personalized CTC datasets, enhances the accuracy of CTC detection and counting, and advances the application of deep learning in this field.

High-quality labeled datasets are essential for deep learning. Traditional manual annotation methods are not only costly and inefficient but also pose challenges in specialized domains where expert knowledge is needed. Self-supervised methods, despite leveraging unlabeled data for feature extraction, still require hundreds or thousands of labeled instances to guide the model for effective specialized image classification. Current unsupervised learning methods offer automatic classification without prior annotation but often compromise on accuracy. As a result, efficiently procuring high-quality labeled datasets remains a pressing challenge for specialized domain images devoid of annotated data. Addressing this, an unsupervised classification method with three key ideas is introduced: 1) dual-step feature dimensionality reduction using a pre-trained model and manifold learning, 2) a voting mechanism from multiple clustering algorithms, and 3) post-hoc instead of prior manual annotation. This approach outperforms supervised methods in classification accuracy, as demonstrated with fungal image data, achieving 94.1% and 96.7% on public and private datasets respectively. The proposed unsupervised classification method reduces dependency on pre-annotated datasets, enabling a closed-loop for data classification. The simplicity and ease of use of this method will also bring convenience to researchers in various fields in building datasets, promoting AI applications for images in specialized domains.

As human activities intensify, environmental systems such as aquatic ecosystems and water treatment systems face increasingly complex pressures, impacting ecological balance, public health, and sustainable development, making intelligent anomaly monitoring essential. However, traditional monitoring methods suffer from delayed responses, insufficient data processing capabilities, and weak generalisation, making them unsuitable for complex environmental monitoring needs.In recent years, machine learning has been widely applied to anomaly detection, but the multi-dimensional features and spatiotemporal dynamics of environmental ecological data, especially the long-term dependencies and strong variability in the time dimension, limit the effectiveness of traditional methods.Deep learning, with its ability to automatically learn features, captures complex nonlinear relationships, improving detection performance. However, its application in environmental monitoring is still in its early stages and requires further exploration.This paper introduces a new deep learning method, Time-EAPCR (Time-Embedding-Attention-Permutated CNN-Residual), and applies it to environmental science. The method uncovers feature correlations, captures temporal evolution patterns, and enables precise anomaly detection in environmental systems.We validated Time-EAPCR's high accuracy and robustness across four publicly available environmental datasets. Experimental results show that the method efficiently handles multi-source data, improves detection accuracy, and excels across various scenarios with strong adaptability and generalisation. Additionally, a real-world river monitoring dataset confirmed the feasibility of its deployment, providing reliable technical support for environmental monitoring.

With the advancement of Industry 4.0, intelligent manufacturing extensively employs sensors for real-time multidimensional data collection, playing a crucial role in equipment monitoring, process optimisation, and efficiency enhancement. Industrial data exhibit characteristics such as multi-source heterogeneity, nonlinearity, strong coupling, and temporal interactions, while also being affected by noise interference. These complexities make it challenging for traditional anomaly detection methods to extract key features, impacting detection accuracy and stability. Traditional machine learning approaches often struggle with such complex data due to limitations in processing capacity and generalisation ability, making them inadequate for practical applications. While deep learning feature extraction modules have demonstrated remarkable performance in image and text processing, they remain ineffective when applied to multi-source heterogeneous industrial data lacking explicit correlations. Moreover, existing multi-source heterogeneous data processing techniques still rely on dimensionality reduction and feature selection, which can lead to information loss and difficulty in capturing high-order interactions. To address these challenges, this study applies the EAPCR and Time-EAPCR models proposed in previous research and introduces a new model, Time-EAPCR-T, where Transformer replaces the LSTM module in the time-series processing component of Time-EAPCR. This modification effectively addresses multi-source data heterogeneity, facilitates efficient multi-source feature fusion, and enhances the temporal feature extraction capabilities of multi-source industrial data.Experimental results demonstrate that the proposed method outperforms existing approaches across four industrial datasets, highlighting its broad application potential.