A Bayesian model for anomaly detection in SQL databases for security systems

The world health organization recommends visual inspection with acetic acid (VIA) and/or Lugol’s Iodine (VILI) for cervical cancer screening in low-resource settings. Human interpretation of diagnostic indicators for visual inspection is qualitative, subjective, and has high inter-observer discordance, which could lead both to adverse outcomes for the patient and unnecessary follow-ups. In this work, we a simple method for automatic feature extraction and classification for Lugol’s Iodine cervigrams acquired with a low-cost, miniature, digital colposcope. Algorithms to preprocess expert physician-labelled cervigrams and to extract simple but powerful color-based features are introduced. The features are used to train a support vector machine model to classify cervigrams based on expert physician labels. The selected framework achieved a sensitivity, specificity, and accuracy of 89.2%, 66.7% and 80.6% with majority diagnosis of the expert physicians in discriminating cervical intraepithelial neoplasia (CIN +) relative to normal tissues. The proposed classifier also achieved an area under the curve of 84 when trained with majority diagnosis of the expert physicians. The results suggest that utilizing simple color-based features may enable unbiased automation of VILI cervigrams, opening the door to a full system of low-cost data acquisition complemented with automatic interpretation.

Fuzzy anomaly scores for Isolation Forest

Abstract. Determination of the maximum ability for feature extraction from satellite imageries based on ontology procedure using cartographic feature determination is the main objective of this research. Therefore, a special ontology has been developed to extract maximum volume of information available in different high resolution satellite imageries and compare them to the map information layers required in each specific scale due to unified specification for surveying and mapping. ontology seeks to provide an explicit and comprehensive classification of entities in all sphere of being. This study proposes a new method for automatic maximum map feature extraction and reconstruction of high resolution satellite images. For example, in order to extract building blocks to produce 1 : 5000 scale and smaller maps, the road networks located around the building blocks should be determined. Thus, a new building index has been developed based on concepts obtained from ontology. Building blocks have been extracted with completeness about 83%. Then, road networks have been extracted and reconstructed to create a uniform network with less discontinuity on it. In this case, building blocks have been extracted with proper performance and the false positive value from confusion matrix was reduced by about 7%. Results showed that vegetation cover and water features have been extracted completely (100%) and about 71% of limits have been extracted. Also, the proposed method in this article had the ability to produce a map with largest scale possible from any multi spectral high resolution satellite imagery equal to or smaller than 1 : 5000.

Ultrasound images of muscle fascicles have been widely used to investigate muscle properties under static/dynamic and pathologic conditions. Fascicle images are usually detected and measured manually, which is subjective and time consuming, especially when dealing with large number of images. In this study, an automatic linear extraction method based on localized Radon transform and revoting strategy is proposed to detect and track muscle fascicles in ultrasound images. The performance of the proposed method is compared to another automatic linear feature extraction method of revoting Hough transform using both simulated images generated by Field II and clinical images from two human subjects. The proposed tracking method is further validated using experimental data. Both the simulation and experimental results show that the proposed method is robust in the presence of speckle noise, accurate in terms of orientation and position measurement, and feasible for analyzing clinical data.

After a frequency-domain-preprocessing of any standard 2D images, the standard patterns to be learned can generally be presented by N-D analog vectors. When these vectors satisfy the most general separability condition, the positive linear independency (or PLI) condition, these vectors can definitely be learned by a one-layered, hard-limited perceptron in a noniterative manner. From this noniterative learning scheme, an automatic feature extraction and automatic feature competition method can be derived which will enhance significantly the robustness in the recognition mode. This paper reports the theoretical analysis of this novel feature extraction scheme and the experimental result demonstrating the robustness of recognition and the speed of learning of this scheme. Comparison of this novel feature extraction scheme with Karhunen-Loeve scheme and the SVD (singular value decomposition) scheme is discussed in detail.

Tail rotor bearing is the key components of Unmanned Aerial Vehicle (UAV) tail rotor to help the tail rotor blade to keep the balance and control the course. The previous researches about tail rotor bearing diagnosis are based on vibration, acoustic, temperature and others. However, the existing monitoring signals are easily contaminated by environment or measurement noises and fail to detect early fault with high accuracy. To overcome this challenge, this paper utilizes the ultrasound signal to monitor health condition of tail rotor bearing, and proposes an automatic feature extraction and fusion method. In our proposed method, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is first used decompose the ultrasound signal into several intrinsic mode functions (IMFs) containing different fault-related information. Then, we design an attention-based weight module to dynamically assign different weights to each IMFs. Finally, the weighted IMFs are fed to a CNN-based feature extraction module to perform feature learning and classification. A Unmanned Aerial vehicle (UAV) rotor simulation bench has been setup to validate the performance of our proposed method. Experimental results illustrate that the proposed approach can effectively decompose and extract the discriminative fault features of Unmanned Aerial vehicle (UAV) tail rotor bearing and achieved superior diagnosis performance.

Explaining anomalies in coal proximity and coal processing data with Shapley and tree-based models

Most of the existing smoke detection methods are based on manual operation, which is difficult to meet the needs of fire monitoring. To further improve the accuracy of smoke detection, an automatic feature extraction and classification method based on fast regional convolution neural network (fast R–CNN) was introduced in the study. This method uses a selective search algorithm to obtain the candidate images of the sample images. The preselected area coordinates and the sample image of visual task are used as network learning. During the training process, we use the feature migration method to avoid the lack of smoke data or limited data sources. Finally, a target detection model is obtained, which is strongly related to a specified visual task, and it has well-trained weight parameters. Experimental results show that this method not only improves the detection accuracy but also effectively reduces the false alarm rate. It can not only meet the real time and accuracy of fire detection but also realize effective fire detection. Compared with similar fire detection algorithms, the improved algorithm proposed in this paper has better robustness to fire detection and has better performance in accuracy and speed.

A novel online tool condition monitoring method for milling titanium alloy with consideration of tool wear law

The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM) was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved.

In vivo confocal microscopy (IVCM) is a crucial imaging modality for assessing corneal diseases, yet distinguishing pathological features from normal variations remains challenging due to the complex multi-layered corneal structure. Existing anomaly detection methods often struggle to generalize across diverse disease manifestations. To address these limitations, we propose a Transformer-based unsupervised anomaly detection method for IVCM images, capable of identifying corneal abnormalities without prior knowledge of specific disease features. Our method consists of three submodules: an EfficientNet network, a Multi-Scale Feature Fusion Network, and a Transformer Network. A total of 7,063 IVCM images (95 eyes) were included for analysis. The model was trained exclusively on normal IVCM images to capture and differentiate structural variations across four distinct corneal layers: epithelium, sub-basal nerve plexus, stroma, and endothelium. During inference, anomaly scores were computed to distinguish pathological from normal images. The model's performance was evaluated on both internal and external datasets, and comparative analyses were conducted against existing anomaly detection methods, including generative adversarial networks (AnoGAN), generate to detect anomaly model (G2D), and discriminatively trained reconstruction anomaly embedding model (DRAEM). Additionally, explainable anomaly maps were generated to enhance the interpretability of model decisions. The proposed method achieved an the areas under the receiver operating characteristic curve of 0.933 on internal validation and 0.917 on an external test dataset, outperforming AnoGAN, G2D, and DRAEM in both accuracy and generalizability. The model effectively distinguished normal and pathological images, demonstrating statistically significant differences in anomaly scores (p < 0.001). Furthermore, visualization results indicated that the detected anomalous regions corresponded to morphological deviations, highlighting potential imaging biomarkers for corneal diseases. This study presents an efficient and interpretable unsupervised anomaly detection model for IVCM images, effectively identifying corneal abnormalities without requiring labeled pathological samples. The proposed method enhances screening efficiency, reduces annotation costs, and holds great potential for scalable intelligent diagnosis of corneal diseases.

Anomalous actors are becoming increasingly sophisticated both in methodology and technical ability. Fortunately, the companies impacted by anomalous behaviour are also generating more data and insights on potential anomalous cases than ever before. In this paper, a unified approach to managing the complexity of constructing a useable anomaly detection system is presented. The unified approach is comprised of three algorithms, a Neural Architecture Search (NAS) implementation for autoencoders, an anomaly score threshold optimisation algorithm, and a Gaussian scaling function for anomaly scores. NAS is applied to a data set containing instances of credit card fraud. The NAS algorithm is used to simulate a population of 50 candidate deep learning architectures, with the best performing architecture being selected based on a balanced score, comprised of an average of the Area under the ROC curve, Average Precision and normalised Matthews Correlation Coefficient scores. The threshold optimisation algorithm is used to determine the appropriate threshold between the classes, for the purposes of producing the binary classification outcome of each architecture. The Gaussian scaling algorithm is applied to the raw anomaly scores of the optimal architecture into order to generate useable probability scores. Not only did the proposed unified approach simplify the process of selecting an optimal neural architecture whose output is interpretable by business practitioners and comparable with other probability score producing models, but it also contributes to anomaly detection in a transactional setting by eliminating subjective thresholds when classifying anomalous transactions.

The widespread application of graph data in various high-risk scenarios has increased attention to graph anomaly detection (GAD). Faced with real-world graphs that often carry node descriptions in the form of raw text sequences, termed text-attributed graphs (TAGs), existing graph anomaly detection pipelines typically involve shallow embedding techniques to encode such textual information into features, and then rely on complex self-supervised tasks within the graph domain to detect anomalies. However, this text encoding process is separated from the anomaly detection training objective in the graph domain, making it difficult to ensure that the extracted textual features focus on GAD-relevant information, seriously constraining the detection capability. How to seamlessly integrate raw text and graph topology to unleash the vast potential of cross-modal data in TAGs for anomaly detection poses a challenging issue. This paper presents a novel end-to-end paradigm for text-attributed graph anomaly detection, named CMUCL. We simultaneously model data from both text and graph structures, and jointly train text and graph encoders by leveraging cross-modal and uni-modal multi-scale consistency to uncover potential anomaly-related information. Accordingly, we design an anomaly score estimator based on inconsistency mining to derive node-specific anomaly scores. Considering the lack of benchmark datasets tailored for anomaly detection on TAGs, we release 8 datasets to facilitate future research. Extensive evaluations show that CMUCL significantly advances in text-attributed graph anomaly detection, delivering an 11.13% increase in average accuracy (AP) over the suboptimal.

Unsupervised anomaly detection algorithm is typically suitable only to a specific type of anomaly, among point anomaly, collective anomaly, and contextual anomaly. A mismatch between the intended anomaly type of an algorithm and the actual type in the data can lead to poor performance. In this paper, utilizing Hilbert–Schmidt independence criterion (HSIC), we propose an unsupervised backward elimination feature selection algorithm BAHSIC-AD to identify a subset of features with the strongest interdependence for anomaly detection. Using BAHSIC-AD, we compare the effectiveness of a recent Spectral Ranking for Anomalies (SRA) algorithm with other popular anomaly detection methods on a few synthetic datasets and real-world datasets. Furthermore, we demonstrate that SRA, combined with BAHSIC-AD, can be a generally applicable method for detecting point, collective, and contextual anomalies.

BACKGROUND Patient heterogeneity is a key challenge in immunotherapy for IDH-wildtype glioblastoma (GBM), where hypermutated tumors or highly immunosuppressive tumor microenvironments (TME) act as clinical outliers affecting treatment response and trial stratification. We developed Alert-GBM, a radiogenomic AI model designed to flag such outliers based on radiomic signatures from diagnostic imaging. MATERIAL AND METHODS We used multicenter open-access radiogenomic datasets (n = 176) to train unsupervised outlier detection models. Principal Component Analysis (PCA) served as a first-pass filter to harmonize data before applying Isolation Forest (IF) modeling. Three IF models were trained using inter-dataset leave-one-out cross-validation (LOOCV) to simulate real-world performance and were benchmarked against each other. The final model was selected using stratified 10-fold cross-validation (CV). Outliers were validated through visual inspection, statistical profiling, comparison with other outlier detection methods (Local Outlier Factor, One-Class SVM, Mahalanobis distance), and correlation with biological and immune profiles from imaging and omics data. RESULTS The PCA filter identified 3 initial outliers based on MRI metadata. The final IF model, following stratified 10-fold CV, detected 6 outliers across the datasets, with anomaly scores plotted. Flagged cases included large, highly enhancing tumors, minimally enhancing tumors, and post-operative scans. Visualizations using PCA, t-SNE, and UMAP were generated to illustrate separability. False positives and negatives were assessed using immune-based scores, and the distribution of anomaly scores was analyzed with KDE plots. Cross-validation against alternative outlier models confirmed consistency of the flagged cases. CONCLUSION Alert-GBM is a proof-of-concept AI architecture for outlier detection in GBM MRI radiogenomics, capable of flagging cases with atypical immune TME profiles. Integrating such models with radiogenomic immune predictors at the time of diagnosis may support multidisciplinary decision-making and improve patient stratification for immunotherapy trials. Incorporating a human-in-the-loop framework ensures that AI outputs remain clinically interpretable and actionable.