Improvement In F1 Score Research Articles

Inductive Attributed Community Search: To Learn Communities Across Graphs

Attributed community search (ACS) aims to identify subgraphs satisfying both structure cohesiveness and attribute homogeneity in attributed graphs, for a given query that contains query nodes and query attributes. Previously, algorithmic approaches deal with ACS in a two-stage paradigm, which suffer from structural inflexibility and attribute irrelevance. To overcome this problem, recently, learning-based approaches have been proposed to learn both structures and attributes simultaneously as a one-stage paradigm. However, these approaches train a transductive model which assumes the graph to infer unseen queries is as same as the graph used for training. That limits the generalization and adaptation of these approaches to different heterogeneous graphs. In this paper, we propose a new framework, Inductive Attributed Community Search, IACS , by inductive learning, which can be used to infer new queries for different communities/graphs. Specifically, IACS employs an encoder-decoder neural architecture to handle an ACS task at a time, where a task consists of a graph with only a few queries and corresponding ground-truth. We design a three-phase workflow, "training-adaptation-inference", which learns a shared model to absorb and induce prior effective common knowledge about ACS across different tasks. And the shared model can swiftly adapt to a new task with small number of ground-truth. We conduct substantial experiments in 7 real-world datasets to verify the effectiveness of IACS for CS/ACS. Our approach IACS achieves 28.97% and 25.60% improvements in F1-score on average in CS and ACS, respectively.

Exploiting ChatGPT for Diagnosing Autism-Associated Language Disorders and Identifying Distinct Features.

Diagnosing language disorders associated with autism is a complex and nuanced challenge, often hindered by the subjective nature and variability of traditional assessment methods. Traditional diagnostic methods not only require intensive human effort but also often result in delayed interventions due to their lack of speed and specificity. In this study, we explored the application of ChatGPT, a state-of-the-art large language model, to overcome these obstacles by enhancing diagnostic accuracy and profiling specific linguistic features indicative of autism. Leveraging ChatGPT's advanced natural language processing capabilities, this research aims to streamline and refine the diagnostic process. Specifically, we compared ChatGPT's performance with that of conventional supervised learning models, including BERT, a model acclaimed for its effectiveness in various natural language processing tasks. We showed that ChatGPT substantially outperformed these models, achieving over 13% improvement in both accuracy and F1-score in a zero-shot learning configuration. This marked enhancement highlights the model's potential as a superior tool for neurological diagnostics. Additionally, we identified ten distinct features of autism-associated language disorders that vary significantly across different experimental scenarios. These features, which included echolalia, pronoun reversal, and atypical language usage, were crucial for accurately diagnosing ASD and customizing treatment plans. Together, our findings advocate for adopting sophisticated AI tools like ChatGPT in clinical settings to assess and diagnose developmental disorders. Our approach not only promises greater diagnostic precision but also aligns with the goals of personalized medicine, potentially transforming the evaluation landscape for autism and similar neurological conditions.

Intelligent Detection of Surface Defects in High-Speed Railway Ballastless Track Based on Self-Attention and Transfer Learning

The detection of ballastless track surface (BTS) defects is a prerequisite for ensuring the safe operation of high-speed railways. Traditional convolutional neural networks fail to fully exploit contextual information and lack global pixel representations. The extensive stacking of convolutions leads deep learning models to play a black-box detection role, lacking interpretability. Due to the current lack of sufficient high-quality surface data for ballastless tracks, it is a severe constraint on the accurate identification of the substructure state in high-speed railways. This paper proposes an intelligent detection method for BTS defects named TrackNet based on self-attention and transfer learning. The method enhances the fusion ability of global features of BTS defects using multihead self-attention. The model’s dependence on extensive defect data is reduced by transferring knowledge from large-scale publicly available datasets. Experimental results demonstrate that compared to advanced Swin Transformer model results, the TrackNet model achieves improvements in average accuracy and F1-score by 5.15% and 5.16%, respectively, on limited test data. The TrackNet model visualizes the decision regions of the model in identifying BTS defects, revealing the black-box recognition mechanism of deep learning models. This research performs engineering applications and provides valuable insights for the multiclass recognition of BTS defects in high-speed railways.

Tiny machine learning empowers climbing inspection robots for real-time multiobject bolt-defect detection

Ensuring the structural integrity of steel construction is critical, necessitating effective methods for detecting bolt defects. Traditional inspection methods are reliable but require significant labor and struggle with the accessibility of complex structures. This research introduces a real-time bolt-defect detection system that integrates tiny machine learning (TinyML) with a magnetic climbing robot to enhance inspection efficiency and scope. The system employs the faster objects, more objects (FOMO) algorithm optimized for edge computing on microcontrollers. This approach enables accurate bolt identification, including normal, loose, and missing bolts. The average system accuracy is 82%, with precision and recall values from 0.57 to 0.89 and 0.67 to 0.87, respectively. The system demonstrates balanced detection, evidenced by an F1 score improvement of up to 62%. The FOMO model displays compelling performance on defect detection tasks, achieving an F1 score of approximately 75%, outperforming the MobileNetV2 Single Shot Multibox Detector with Feature Pyramid Networks Lite and You Only Look Once version 5 small. The efficiency of the FOMO model is highlighted by its low hardware requirements at less than 0.1 MB of flash memory and 893.8 KB of random access memory for the 32-bit floating-point data format and is reduced for the 8-bit integer data format, with inference times of 142 ms and 86 ms, respectively. These findings contrast with the higher resource demands and slower inference time of the compared models, indicating the suitability of the FOMO model for low-capacity microcontrollers and its feasibility for real-time applications. The performance analysis across scenarios confirms the high precision (average 0.77) and recall (average 0.76), validating the robustness of the model in diverse environmental conditions. The system offers an advancement over traditional bolt-defect detection methods in accuracy and efficiency by leveraging TinyML and a magnetic climbing robot, setting new benchmarks for real-time inspection technology. The quantitative results underscore the performance of the system, presenting a scalable, cost-effective solution for improving the safety and durability of steel structures.

Recurrent event query decoder for document-level event extraction

Document-level event extraction is a challenging task in natural language processing, as it involves multiple events within a document and scattered event arguments across sentences. To tackle these challenges, we propose a recurrent event query decoder, i.e., a recurrent module that dynamically updates event queries to capture cross-event dependencies. Our approach then generates arguments by extracting role-argument relations using bilinear mapping, which helps address the issue of scattered arguments. Experimental results demonstrate that our proposed approach outperforms state-of-the-art models on a large-scale public dataset and actual application data, achieving significant improvements in F1-score. In domain-specific event extraction applications, our method achieves higher accuracy with fewer resources compared to general-purpose large language models.

Wearable sensors in patient acuity assessment in critical care.

Acuity assessments are vital for timely interventions and fair resource allocation in critical care settings. Conventional acuity scoring systems heavily depend on subjective patient assessments, leaving room for implicit bias and errors. These assessments are often manual, time-consuming, intermittent, and challenging to interpret accurately, especially for healthcare providers. This risk of bias and error is likely most pronounced in time-constrained and high-stakes environments, such as critical care settings. Furthermore, such scores do not incorporate other information, such as patients' mobility level, which can indicate recovery or deterioration in the intensive care unit (ICU), especially at a granular level. We hypothesized that wearable sensor data could assist in assessing patient acuity granularly, especially in conjunction with clinical data from electronic health records (EHR). In this prospective study, we evaluated the impact of integrating mobility data collected from wrist-worn accelerometers with clinical data obtained from EHR for estimating acuity. Accelerometry data were collected from 87 patients wearing accelerometers on their wrists in an academic hospital setting. The data was evaluated using five deep neural network models: VGG, ResNet, MobileNet, SqueezeNet, and a custom Transformer network. These models outperformed a rule-based clinical score (Sequential Organ Failure Assessment, SOFA) used as a baseline when predicting acuity state (for ground truth we labeled as unstable patients if they needed life-supporting therapies, and as stable otherwise), particularly regarding the precision, sensitivity, and F1 score. The results demonstrate that integrating accelerometer data with demographics and clinical variables improves predictive performance compared to traditional scoring systems in healthcare. Deep learning models consistently outperformed the SOFA score baseline across various scenarios, showing notable enhancements in metrics such as the area under the receiver operating characteristic (ROC) Curve (AUC), precision, sensitivity, specificity, and F1 score. The most comprehensive scenario, leveraging accelerometer, demographics, and clinical data, achieved the highest AUC of 0.73, compared to 0.53 when using SOFA score as the baseline, with significant improvements in precision (0.80 vs. 0.23), specificity (0.79 vs. 0.73), and F1 score (0.77 vs. 0.66). This study demonstrates a novel approach beyond the simplistic differentiation between stable and unstable conditions. By incorporating mobility and comprehensive patient information, we distinguish between these states in critically ill patients and capture essential nuances in physiology and functional status. Unlike rudimentary definitions, such as equating low blood pressure with instability, our methodology delves deeper, offering a more holistic understanding and potentially valuable insights for acuity assessment.

The art of time-bending: Data augmentation and early prediction for efficient traffic classification

The accurate identification of internet traffic is crucial for network management. However, the use of encryption techniques and constant changes in network protocols make it difficult to extract useful features for traffic classification. Additionally, there may be limited data availability and a lack of diversity within the dataset, which poses further challenges. To address these issues, our research proposes a novel solution that uses an innovative data augmentation technique. This approach leverages the capabilities of LSTM networks to create synthetic data points that closely resemble real traffic data. By doing so, we can significantly enrich the dataset used for training and improve classification efficiency. We conducted thorough experiments to validate our approach and found that combining LSTM-generated data with actual traffic data leads to notable improvements in classification efficiency. We demonstrated the effectiveness of our methodology using academic and commercial datasets. Our classifier, trained on the generated data, showed a performance boost of 6%. Moreover, when classifying with only half of the time, thus utilizing half of the signal, our approach achieved a notable 4% improvement compared to the original classifier. The inclusion of augmented samples within the training set led to a noticeable improvement in both accuracy and F1-score. These findings compellingly demonstrate our data augmentation strategy’s practical utility and efficiency in earlier prediction with improved performance for encrypted traffic classification systems.

BDHE-Net: A Novel Building Damage Heterogeneity Enhancement Network for Accurate and Efficient Post-Earthquake Assessment Using Aerial and Remote Sensing Data

Accurate and efficient post-earthquake building damage assessment methods enable key building damage information to be obtained more quickly after an earthquake, providing strong support for rescue and reconstruction efforts. Although many methods have been proposed, most have limited effect on accurately extracting severely damaged and collapsed buildings, and they cannot meet the needs of emergency response and rescue operations. Therefore, in this paper, we develop a novel building damage heterogeneity enhancement network for pixel-level building damage classification of post-earthquake unmanned aerial vehicle (UAV) and remote sensing data. The proposed BDHE-Net includes the following three modules: a data augmentation module (DAM), a building damage attention module (BDAM), and a multilevel feature adaptive fusion module (MFAF), which are used to alleviate the weight deviation of intact and slightly damaged categories during model training, pay attention to the heterogeneous characteristics of damaged buildings, and enhance the extraction of house integrity contour information at different resolutions of the image. In addition, a combined loss function is used to focus more attention on the small number of severely damaged and collapsed classes. The proposed model was tested on remote sensing and UAV images acquired from the Afghanistan and Baoxing earthquakes, and the combined loss function and the role of the three modules were studied. The results show that compared with the state-of-the-art methods, the proposed BDHE-Net achieves the best results, with an F1 score improvement of 6.19–8.22%. By integrating the DBA, BDAM, and MFAF modules and combining the loss functions, the model’s classification accuracy for severely damaged and collapsed categories can be improved.

Deep Multiscale Soft-Threshold Support Vector Data Description for Enhanced Heavy-Duty Gas Turbine Generator Sets’ Anomaly Detection

This paper introduces an innovative approach, Deep Multiscale Soft-Threshold Support Vector Data Description (DMS-SVDD), designed for the detection of anomalies and prediction of faults in heavy-duty gas turbine generator sets (GENSETs). The model combines a support vector data description (SVDD) with a deep autoencoder backbone network framework, integrating a multiscale convolutional neural network (M) and soft-threshold activation network (S) into the Deep-SVDD framework. In comparison with conventional methods, such as One-Class Support Vector Machine (OCSVM) and autoencoder (AE), DMS-SVDD demonstrates improvements in accuracy (by 22.94%), recall (by 32%), F1 score (by 12.02%), and smoothness (by 39.15%). The model excels particularly in feature extraction, denoising, and early fault detection, offering a proactive strategy for maintenance. Furthermore, the DMS-SVDD demonstrated enhanced training efficiency with a reduction in the convergence rounds by 66% and overall training times by 34.13%. The study concludes that DMS-SVDD presents a robust and efficient solution for gas turbine anomaly detection, with practical advantages for decision support in turbine maintenance. Future research could explore additional refinements and applications of the DMS-SVDD model across diverse industrial contexts.

Combining Multitemporal Optical and Radar Satellite Data for Mapping the Tatra Mountains Non-Forest Plant Communities

Climate change is significantly affecting mountain plant communities, causing dynamic alterations in species composition as well as spatial distribution. This raises the need for constant monitoring. The Tatra Mountains are the highest range of the Carpathians which are considered biodiversity hotspots in Central Europe. For this purpose, microwave Sentinel-1 and optical multi-temporal Sentinel-2 data, topographic derivatives, and iterative machine learning methods incorporating classifiers random forest (RF), support vector machines (SVMs), and XGBoost (XGB) were used for the identification of thirteen non-forest plant communities (various types of alpine grasslands, shrublands, herbaceous heaths, mountain hay meadows, rocks, and scree communities). Different scenarios were tested to identify the most important variables, retrieval periods, and spectral bands. The overall accuracy results for the individual algorithms reached RF (0.83–0.96), SVM (0.87–0.93), and lower results for XGBoost (0.69–0.82). The best combination, which included a fusion of Sentinel-1, Sentinel-2, and topographic data, achieved F1-scores for classes in the range of 0.73–0.97 (RF) and 0.66–0.95 (SVM). The inclusion of topographic variables resulted in an improvement in F1-scores for Sentinel-2 data by one–four percent points and Sentinel-1 data by 1%–9%. For spectral bands, the Sentinel-2 10 m resolution bands B4, B3, and B2 showed the highest mean decrease accuracy. The final result is the first comprehensive map of non-forest vegetation for the Tatra Mountains area.

Combining permuted language model and adversarial training for Chinese machine reading comprehension

Due to the polysemy and complexity of the Chinese language, Chinese machine reading comprehension has always been a challenging task. To improve the semantic understanding and robustness of Chinese machine reading comprehension models, we propose a model that utilizes adversarial training algorithms and Permuted Language Model (PERT). Firstly, we employ the PERT pre-training model to embed paragraphs and questions into vector space to obtain corresponding sequential representations. Secondly, we use a multi-head self-attention mechanism to extract key textual information from the sequence and employ a Bi-GRU network to semantically fuse the output feature vectors, aiming to learn deep semantic representations in the text. Finally, we introduce perturbations into the model training process. We achieve this by utilizing adversarial training algorithms such as Fast Gradient Method (FGM) and Projected Gradient Descent (PGD). These algorithms generate adversarial samples to enhance the model’s robustness and stability when facing diverse inputs. We conducted comparative experiments on the publicly available Chinese reading comprehension datasets CMRC2018 and DRCD. The experimental results show that our proposed model has achieved significant improvements in both EM and F1-Score compared to the baseline model. To validate the model’s generalization and robustness, we utilized ChatGPT to construct a scientific dataset that includes a large number of domain-specific terms, sentences with mixed Chinese and English, and complex comprehension tasks. Our model also performed remarkably well on the self-built dataset. In conclusion, the proposed model not only effectively enhances the understanding of semantic information in Chinese text but also demonstrates a certain level of generalization capability.

MetageNN: a memory-efficient neural network taxonomic classifier robust to sequencing errors and missing genomes.

With the rapid increase in throughput of long-read sequencing technologies, recent studies have explored their potential for taxonomic classification by using alignment-based approaches to reduce the impact of higher sequencing error rates. While alignment-based methods are generally slower, k-mer-based taxonomic classifiers can overcome this limitation, potentially at the expense of lower sensitivity for strains and species that are not in the database. We present MetageNN, a memory-efficient long-read taxonomic classifier that is robust to sequencing errors and missing genomes. MetageNN is a neural network model that uses short k-mer profiles of sequences to reduce the impact of distribution shifts on error-prone long reads. Benchmarking MetageNN against other machine learning approaches for taxonomic classification (GeNet) showed substantial improvements with long-read data (20% improvement in F1 score). By utilizing nanopore sequencing data, MetageNN exhibits improved sensitivity in situations where the reference database is incomplete. It surpasses the alignment-based MetaMaps and MEGAN-LR, as well as the k-mer-based Kraken2 tools, with improvements of 100%, 36%, and 23% respectively at the read-level analysis. Notably, at the community level, MetageNN consistently demonstrated higher sensitivities than the previously mentioned tools. Furthermore, MetageNN requires < 1/4th of the database storage used by Kraken2, MEGAN-LR and MMseqs2 and is > 7× faster than MetaMaps and GeNet and > 2× faster than MEGAN-LR and MMseqs2. This proof of concept work demonstrates the utility of machine-learning-based methods for taxonomic classification using long reads. MetageNN can be used on sequences not classified by conventional methods and offers an alternative approach for memory-efficient classifiers that can be optimized further.

Enhancing Adversarial Learning-Based Change Detection in Imbalanced Datasets Using Artificial Image Generation and Attention Mechanism

Deep Learning (DL) has become a popular method for Remote Sensing (RS) Change Detection (CD) due to its superior performance compared to traditional methods. However, generating extensive labeled datasets for DL models is time-consuming and labor-intensive. Additionally, the imbalance between changed and unchanged areas in object CD datasets, such as buildings, poses a critical issue affecting DL model efficacy. To address this issue, this paper proposes a change detection enhancement method using artificial image generation and attention mechanism. Firstly, the content of the imbalanced CD dataset is enhanced using a data augmentation strategy that synthesizes effective building CD samples using artificial RS image generation and building label creation. The created building labels, which serve as new change maps, are fed into a generator model based on a conditional Generative Adversarial Network (c-GAN) to generate high-resolution RS images featuring building changes. The generated images with their corresponding change maps are then added to the CD dataset to create the balance between changed and unchanged samples. Secondly, a channel attention mechanism is added to the proposed Adversarial Change Detection Network (Adv-CDNet) to boost its performance when training on the imbalanced dataset. The study evaluates the Adv-CDNet using WHU-CD and LEVIR-CD datasets, with WHU-CD exhibiting a higher degree of sample imbalance compared to LEVIR-CD. Training the Adv-CDNet on the augmented dataset results in a significant 16.5% F1-Score improvement for the highly imbalanced WHU-CD. Moreover, comparative analysis showcases the superior performance of the Adv-CDNet when complemented with the attention module, achieving a 6.85% F1-Score enhancement.

Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

Lane detection (LD) plays a crucial role in enhancing the L2+ capabilities of autonomous driving, capturing widespread attention. The Post-Processing Quantization (PTQ) could facilitate the practical application of LD models, enabling fast speeds and limited memories without labeled data. However, prior PTQ methods do not consider the complex LD outputs that contain physical semantics, such as offsets, locations, etc., and thus cannot be directly applied to LD models. In this paper, we pioneeringly investigate semantic sensitivity to post-processing for lane detection with a novel Lane Distortion Score. Moreover, we identify two main factors impacting the LD performance after quantization, namely intra-head sensitivity and inter-head sensitivity, where a small quantization error in specific semantics can cause significant lane distortion. Thus, we propose a Selective Focus framework deployed with Semantic Guided Focus and Sensitivity Aware Selection modules, to incorporate post-processing information into PTQ reconstruction. Based on the observed intra-head sensitivity, Semantic Guided Focus is introduced to prioritize foreground-related semantics using a practical proxy. For inter-head sensitivity, we present Sensitivity Aware Selection, efficiently recognizing influential prediction heads and refining the optimization objectives at runtime. Extensive experiments have been done on a wide variety of models including keypoint-, anchor-, curve-, and segmentation-based ones. Our method produces quantized models in minutes on a single GPU and can achieve 6.4\% F1 Score improvement on the CULane dataset. Code and supplementary statement can be found at https://github.com/PannenetsF/SelectiveFocus.

Abstract 4927: Combining single-cell ATAC and RNA sequencing for supervised cell annotation

Abstract Background: Analysis of samples at the single-cell level offers insights into cellular heterogeneity and cell function. Cell type annotation is the first critical step for performing such an analysis. While current methods primarily utilize single-cell RNA sequencing (scRNA-seq) for annotation, several studies have demonstrated improved classification accuracy by combining scRNA-seq with transposase-accessible chromatin sequencing (ATAC-seq) using unsupervised methods. However, the utility of ATAC-seq features for supervised cell-type annotation has not been explored. Aims/Objectives: The objective of this study was to evaluate the relative performance of supervised cell-type classification using scRNA-seq alone vs. in multimodal combination with ATAC-seq; and how these data interplay with choice of classification and dimensionality reduction methods. Methods: A peripheral-blood mononuclear cell multi-omic dataset from a single, healthy female donor wasanalysed in this study. Ground truth annotations were generated using unsupervised annotation with the weighted nearest neighbour clustering method. Two dimensionality reduction methods (principal component analysis (PCA), single-cell Variational Inference (scVI) autoencoder) and four classification models (logistic regression, random forest, support vector machine (SVM)) were implemented and performance metrics (F1 score, precision, and recall) were compared over 10 bootstrap samples. Results: ATAC-seq features improved annotation quality and prediction confidence when using scVI embeddings, independent of the classifier. The best-performing model (SVM with scVI embeddings) showed an increase from a median macro F1 score of 0.907 (IQR = [0.902, 0.910]) using scRNA-seq alone to 0.946 (IQR = [0.940, 0.949], p &amp;lt;0.05) with ATAC-seq added. For PCA embeddings, improvements in macro F1 score were insignificant. All cell types (B, T, monocytes, natural killer and dendritic cells) showed significant improvements when using ATAC-seq with scVI embeddings. CD4 T effector memory cells showed the largest gain in F1 score (0.112, p &amp;lt;0.01), whilst type-2 conventional dendritic cells showed the smallest improvement (0.006, p &amp;lt;0.05). Prediction confidence was improved in B cells, monocytes, natural killer cells, CD4 and CD8 naïve cells, CD4 T central memory cells and CD8 T effector memory cells. Improvements in F1 scores were lost when only classifying major cell types rather than subtypes. Conclusions: Employing ATAC-seq embeddings with scVI autoencoder enhances supervised annotation quality over scRNA-only methods. Further studies should explore the use of ATAC to improve the annotation of highly heterogeneous tissues such as tumours. Citation Format: Jaidip Gill, Abhijit Dasgupta, Brychan Manry, Natasha Markuzon. Combining single-cell ATAC and RNA sequencing for supervised cell annotation [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4927.

A Comparative Study and Improved Bearing Fault Classifier Using Raw Vibration Data Under Limited Training Samples

Artificial intelligence is gaining traction in bearing fault detection and diagnosis. Generally, signal processing and feature selection are carried out to facilitate the fault classification process; however, classification accuracy tends to degrade under limited training data. In this paper, various artificial intelligence (AI) classification models are studied and compared using raw vibration data without signal processing and feature engineering. A Cosine k-Nearest Neighbours (CosKNN)-based classification model is optimized by integrating a Segmentive Mechanism, resulting in an overall classification F1-score improvement to 90.8% compared to the original classifier's 76.9%. The comparative findings show that the proposed model is suitable for circumstances with limited availability of training data, signal processing tools, and feature engineering tuning.

Multiple distresses detection for Asphalt Pavement using improved you Only Look Once Algorithm based on convolutional neural network

ABSTRACT Leveraging the YOLOv7 object detection framework, this study introduces YOLOv7-CSP, a refined algorithm tailored for identifying asphalt pavement distress with enhanced precision. Utilizing advanced image processing for dataset preprocessing, including data augmentation and denoising, YOLOv7-CSP integrates the CSPNeXt structure and CA attention mechanism for improved detection accuracy and efficiency. The algorithm optimizes anchor box selection through Kmeans clustering and employs a secondary labeling method to enhance learning efficiency and dataset quality. Comparative tests reveal YOLOv7-CSP's superior performance, with significant improvements in mAP, F1 score, GFLOPS, and FPS metrics, demonstrating its effectiveness in detecting various pavement distresses. This innovative approach marks a significant advancement in automatic pavement distress recognition, offering a robust solution for highway maintenance decision-making.

Leveraging past information and machine learning to accelerate land disturbance monitoring

Near real-time (NRT) monitoring of land disturbances holds great importance for delivering emergency aid, mitigating negative social and ecological impacts, and distributing resources for disaster recovery. Many past NRT techniques were built upon examining the overall change magnitude of a spectral anomaly with a predefined threshold, namely the unsupervised approach. However, their lack of fully considering spectral change direction, change date, and pre-disturbance conditions often led to low detection sensitivity and high commission errors, especially when only a few satellite observations were available at the early disturbance stage, eventually resulting in a longer lag to produce a reliable disturbance map. For this study, we developed a novel supervised machine learning approach guided by historical disturbance datasets to accelerate land disturbance monitoring. This new approach consisted of two phases. For the first phase, the supervised approach applied retrospective analysis on historical Harmonized Landsat Sentinel-2 (HLS) datasets from 2015 to 2021, combined with several open disturbance products. The disturbance model was constructed for each condition of consecutive anomaly number, with the aim of enhancing the specificity for delineating early-stage disturbance regions. Then, these stage-based models were applied for an NRT scenario to predict disturbance probabilities with 2022 HLS images incrementally on a weekly basis. To demonstrate the capability of this new approach, we developed an operational NRT system incorporating both the unsupervised and supervised approach. Latency and accuracy were evaluated against 3000 samples that were randomly selected from the five most influential disturbance events of the United States in 2022, based on labels and disturbance dates interpreted from daily PlanetScope images. The evaluation showed that the supervised approach required 15 days (since the start of the disturbance event) to reach the plateau of its F1 curve (where most disturbance pixels are detected with high confidence), seven days earlier with roughly 0.2 F1 score improvement compared to the unsupervised approach (0.733 vs. 0.546 F1 score). Further analysis showed the improvement was mainly due to the substantial decrease in commission errors (17.7% vs 44.4%). The latency component analysis illustrated that the supervised approach only took an average of 4.1 days to yield the first disturbance alert at its fastest daily updating speed, owing to its decreased sensitivity lag. This finding highlighted the importance of using past knowledge and machine learning to reduce detection delays for an NRT monitoring task.

Deep Learning for Intrusion Detection Systems (IDSs) in Time Series Data

The advent of computer networks and the internet has drastically altered the means by which we share information and interact with each other. However, this technological advancement has also created opportunities for malevolent behavior, with individuals exploiting vulnerabilities to gain access to confidential data, obstruct activity, etc. To this end, intrusion detection systems (IDSs) are needed to filter malicious traffic and prevent common attacks. In the past, these systems relied on a fixed set of rules or comparisons with previous attacks. However, with the increased availability of computational power and data, machine learning has emerged as a promising solution for this task. While many systems now use this methodology in real-time for a reactive approach to mitigation, we explore the potential of configuring it as a proactive time series prediction. In this work, we delve into this possibility further. More specifically, we convert a classic IDS dataset to a time series format and use predictive models to forecast forthcoming malign packets. We propose a new architecture combining convolutional neural networks, long short-term memory networks, and attention. The findings indicate that our model performs strongly, exhibiting an F1 score and AUC that are within margins of 1% and 3%, respectively, when compared to conventional real-time detection. Also, our architecture achieves an ∼8% F1 score improvement compared to an LSTM (long short-term memory) model.

Identifying galaxy cluster mergers with deep neural networks using idealized Compton-y and X-ray maps

ABSTRACT We present a novel approach to identify galaxy clusters that are undergoing a merger using a deep learning approach. This paper uses massive galaxy clusters spanning 0 ≤ z ≤ 2 from The Three Hundred project, a suite of hydrodynamic resimulations of 324 large galaxy clusters. Mock, idealized Compton-y and X-ray maps were constructed for the sample, capturing them out to a radius of 2R200. The idealized nature of these maps mean they do not consider observational effects such as foreground or background astrophysical objects, any spatial resolution limits or restriction on X-ray energy bands. Half of the maps belong to a merging population as defined by a mass increase ΔM/M ≥ 0.75, and the other half serves as a controlled, relaxed population. We employ a convolutional neural network architecture and train the model to classify clusters into one of the groups. A best-performing model was able to correctly distinguish between the two populations with a balanced accuracy (BA) and recall of 0.77, ROC-AUC of 0.85, PR-AUC of 0.55, and F1 score of 0.53. Using a multichannel model relative to a single-channel model, we obtain a 3 per cent improvement in BA score, and a 6 per cent improvement in F1 score. We use a saliency interpretation approach to discern the regions most important to each classification decision. By analysing radially binned saliency values we find a preference to utilize regions out to larger distances for mergers with respect to non-mergers, greater than ∼1.2R200 and ∼0.7R200 for SZ and X-ray, respectively.