Automatic Annotation Research Articles

The interplay of conceptualization and case marking in the directional cases of Udmurt

Abstract In this paper I discuss the variation among the directional cases in Udmurt (Permic, Uralic). Udmurt has a spatial case system consisting of seven cases in total, of which four are directional cases. Two of the directional cases, elative and egressive, express the source of an action, and two, illative and terminative, the goal of an action. Previous accounts have established that the distinguishing factor between the pairs is the expression of some limit. Egressive and terminative are used to express beginning and end limit, respectively, whereas elative and illative are seen not to express a limit. This kind of distinction in a spatial case system is typologically extremely rare. Especially a case dedicated for starting limit seems not to be attested anywhere else than in the Permic languages, Udmurt, and its closes relative Komi. The explanation for the variation between the cases given in previous research, namely that egressive and terminative express a limit, whereas elative and illative do not, seems not to be general enough, however. Especially, in the spatial domain there are examples where, e.g., illative is said to express the endpoint of movement, and terminative the end limit of a movement, but the depicted situations seem basically identical. Therefore, I suggest that there is a more general tendency of using the limit cases to construe an event as bounded from the beginning or the end, respectively, whereas the non-limit cases is used when the construal does not include a boundary of the event, or the boundary is backgrounded. To explore this possibility, I conduct a qualitative analysis of the senses of each case, as well as a quantitative analysis exploring the effects of different aspects of verbal semantics on the choice between the limit and non-limit cases in the spatial domain. The dataset is 500 manually annotated and analyzed examples of Udmurt literary language, mostly newspaper texts. The process is done manually, as the automatic annotation of the original corpus yields too many false positives when queried for instances of cases. The qualitative analysis is conducted by the Principled Polysemy approach, which yields reliable results on the semantic structure of spatial elements in general. The quantitative analysis is done by implementing a random forest analysis on the dataset. Random forest is chosen for the method because the dataset is somewhat small, and the data points cannot be considered independent. The qualitative analysis reveals that the limit cases are indeed used to express senses like the beginning or end of a timespan or a change in amount, which seem to incorporate a boundary of the event. In contrast, the non-limit cases are used to express senses where the boundary is implied but backgrounded. The quantitative analysis reveals that the semantics of the verb indeed do play a role in the choice between the limit and non-limit cases in the spatial domain. However, due to the nature of the data and the chosen methodology it is not possible to say how exactly the semantics of the verb affect the choice between cases. Nonetheless, the results firmly point to the direction that the difference between the limit and non-limit cases should be analyzed as a difference in the construal of the events, which then have special cases depending on the exact situation expressed.

Text Command Intelligent Understanding for Cybersecurity Testing

Research on named entity recognition (NER) and command-line generation for network security evaluation tools is relatively scarce, and no mature models for recognition or generation have been developed thus far. Therefore, in this study, the aim is to build a specialized corpus for network security evaluation tools by combining knowledge graphs and information entropy for automatic entity annotation. Additionally, a novel NER approach based on the KG-BERT-BiLSTM-CRF model is proposed. Compared to the traditional BERT-BiLSTM model, the KG-BERT-BiLSTM-CRF model demonstrates superior performance when applied to the specialized corpus of network security evaluation tools. The graph attention network (GAT) component effectively extracts relevant sequential content from datasets in the network security evaluation domain. The fusion layer then concatenates the feature sequences from the GAT and BiLSTM layers, enhancing the training process. Upon successful NER execution, in this study, the identified entities are mapped to pre-established command-line data for network security evaluation tools, achieving automatic conversion from textual content to evaluation commands. This process not only improves the efficiency and accuracy of command generation but also provides practical value for the development and optimization of network security evaluation tools. This approach enables the more precise automatic generation of evaluation commands tailored to specific security threats, thereby enhancing the timeliness and effectiveness of cybersecurity defenses.

Quantitative Standardized Expansion Assay: An Artificial Intelligence-Powered Morphometric Description of Blastocyst Expansion and Zona Thinning Dynamics

Artificial intelligence applied to time-lapse microscopy may revolutionize embryo selection in IVF by automating data collection and standardizing the assessments. In this context, blastocyst expansion dynamics, although being associated with reproductive fitness, have been poorly studied. This retrospective study (N = 2184 blastocysts from 786 cycles) exploited both technologies to picture the association between embryo and inner-cell-mass (ICM) area in µm2, the ICM/Trophectoderm ratio, and the zona pellucida thickness in µm (zp-T) at sequential blastocyst expansion stages, with (i) euploidy and (ii) live-birth per transfer (N = 548 transfers). A quantitative-standardized-expansion-assay (qSEA) was also set-up; a novel approach involving automatic annotations of all expansion metrics every 30 min across 5 h following blastulation. Multivariate regressions and ROC curve analyses were conducted. Aneuploid blastocysts were slower, expanded less and showed thicker zp. The qSEA outlined faster and more consistent zp thinning processes among euploid blastocysts, being more or as effective as the embryologists in ranking euploid embryo as top-quality of their cohorts in 69% of the cases. The qSEA also outlined faster and more consistent blastocyst expansion and zp thinning dynamics among euploid implanted versus not implanted blastocysts, disagreeing with embryologists’ priority choice in about 50% of the cases. In conclusion, qSEA is a promising objective, quantitative, and user-friendly strategy to predict embryo competence that now deserves prospective validations.

Publishing and using parliamentary Linked Data on the Semantic Web: ParliamentSampo system for Parliament of Finland

This paper presents a new infrastructure and semantic portal called ParliamentSampo for studying parliamentary speeches, culture, language, and activities in Finland. For the first time, the entire time series of some million plenary speeches of the Parliament of Finland (PoF) since 1907 have been converted from text into knowledge graphs and data services in unified formats, including CSV, Parla-CLARIN, ParlaMint, and RDF Linked Open Data (LOD). The speech data have been interlinked with a semi-automatically created ontology and a knowledge graph about the activities of over 2800 Members of Parliament (MP) and other speakers in the plenary sessions of the PoF. The data was enriched by data linking to external data sources and by reasoning into a broader LOD service. Knowledge extraction techniques based on Natural Language Processing (NLP) were used for automatic semantic annotations and topical classification of the speeches. The data and data services have been used in Digital Humanities (DH) research projects and for application development, especially for developing the in-use semantic portal ParliamentSampo. The infrastructure and the portal were published on February 14th 2023 on the Web using the open CC BY 4.0 license, and quickly gathered thousands of users, including citizens, media, politicians, and researchers of politics. ParliamentSampo is a new member in the “Sampo” series of over 20 interlinked LOD services and semantic portals in Finland, based on a national Semantic Web infrastructure. Although the paper uses Finnish parliamentary data as a case study, the approach, methods, and tools presented can be adapted also to other parliamentary datasets in other countries.

Testing the accuracy of automatic ECG-annotation for suspected acute coronary syndrome

Abstract Background Correct interpretation of ECG recordings plays a crucial role in cardiology. ECG recordings are performed immediately in order to guide treatment of patients with suspected acute coronary syndrome (ACS). Non-cardiologists usually rely on automated manufacturer-derived ECG interpretation. The main purpose of these methods is to detect lifethreatening ECG patterns with high sensitivity, at cost of specificity. However, as yet, the accuracy of these automatic annotations has not been tested in investigator-initiated (IIT) clinical studies. Purpose To test the accuracy of automated ECG annotation provided by the largest ECG manufacturer in Germany in patients undergoing coronary angiography (CA), because of biomarker-positive suspected ACS. Methods We retrospectively identified patients presenting with suspected ACS to two large tertiary hospitals between 2014 – 2021. Inclusion criteria were defined as indication for CA because of biomarker-positive suspected ACS and availability of ECG raw-data. Patients with ST-elevation myocardial infarction were excluded from this analysis. All ECGs were classified as non-indicative or indicative for ischaemia, according to automatic annotations provided by the ECG-manufacturer. The primary endpoint of the study was type 1 myocardial infarction requiring revascularization. Secondary endpoints were identification of coronary artery disease (CAD) with or without revascularization and intrahospital mortality. The association of ECG-abnormalities with the primary and secondary endpoints was tested using logistic-regression analysis. Confidence intervals were calculated using bootstrapping. Results We screened 9,598 patients for eligibility and finally included 2,073 patients meeting the inclusion und exclusion criteria. The median age was 73 years (IQR 61 – 80), 661 (32%) of the patients were females. Among those patients 1,299 (63%) were diagnosed with type 1 myocardial infarction requiring revascularization, 475 patients (23%) didn’t show signs of CAD and 153 patients (7%) died during the index hospital stay. Automatic annotation of ECG-abnormalities was significantly associated with the primary endpoint (OR 1.36; 95% CI 1.14 – 1.63; p < 0.001), and secondary endpoints (OR 1.72; 95% CI 1.39 – 2.13; p < 0.001 for CAD and 1.61; 95% CI 1.16-2.24; p = 0.005 for mortality). The overall sensitivity, specificity and negative predictive value of the method was 47% (45-50%), 60% (57-63%), and 41% (38-43%), respectively. The sensitivity and specificity for different subgroups is illustrated in Figure 1. Conclusion Current manufacturer algorithms for automatic ECG-annotation show a statistically significant association with CAD requiring revascularization. However, 59% of the patients requiring revascularization are not identified with the annotated ECG-abnormalities. Application of artificial intelligence might improve these algorithms and allow safe application of the method in clinical practice.Figure 1

Segmentation of multi-view video speed extraction method that can cross lane dividing lines

Aiming at the problem that the existing video traffic parameter extraction methods are overly dependent on manual annotation and a single perspective cannot effectively correct the dynamic driving deviation of vehicles on site, a multi-perspective video traffic parameter extraction method that can segment and cross lane dividing lines is proposed. The method consists of an automatic annotation point generation module and a multi-perspective correction module. The automatic annotation point generation module realizes the process of automatically generating annotation points by constructing a reference block based on equal-length lane dividing lines. The multi-perspective correction module proposes multiple mapping methods between vehicles and lane dividing lines and a correction speed measurement method based on the average speed probability density function to correct the two types of deviations generated by vehicles during dynamic driving. Experimental results on public data sets and measured data sets show that the vehicle speed extraction accuracy of the proposed method is better than other speed measurement methods, and it has a certain degree of universality.

Semantic Enrichment of a BIM Model Using Revit: Automatic Annotation of Doors in High-Rise Residential Building Models Using Machine Learning

Semantic Enrichment of a BIM Model Using Revit: Automatic Annotation of Doors in High-Rise Residential Building Models Using Machine Learning

Integrating Automated Labeling Framework for Enhancing Deep Learning Models to Count Corn Plants Using UAS Imagery.

Plant counting is a critical aspect of crop management, providing farmers with valuable insights into seed germination success and within-field variation in crop population density, both of which are key indicators of crop yield and quality. Recent advancements in Unmanned Aerial System (UAS) technology, coupled with deep learning techniques, have facilitated the development of automated plant counting methods. Various computer vision models based on UAS images are available for detecting and classifying crop plants. However, their accuracy relies largely on the availability of substantial manually labeled training datasets. The objective of this study was to develop a robust corn counting model by developing and integrating an automatic image annotation framework. This study used high-spatial-resolution images collected with a DJI Mavic Pro 2 at the V2-V4 growth stage of corn plants from a field in Wooster, Ohio. The automated image annotation process involved extracting corn rows and applying image enhancement techniques to automatically annotate images as either corn or non-corn, resulting in 80% accuracy in identifying corn plants. The accuracy of corn stand identification was further improved by training four deep learning (DL) models, including InceptionV3, VGG16, VGG19, and Vision Transformer (ViT), with annotated images across various datasets. Notably, VGG16 outperformed the other three models, achieving an F1 score of 0.955. When the corn counts were compared to ground truth data across five test regions, VGG achieved an R2 of 0.94 and an RMSE of 9.95. The integration of an automated image annotation process into the training of the DL models provided notable benefits in terms of model scaling and consistency. The developed framework can efficiently manage large-scale data generation, streamlining the process for the rapid development and deployment of corn counting DL models.

Efficient Real-Time Droplet Tracking in Crop-Spraying Systems

Spray systems in agriculture serve essential roles in the precision application of pesticides, fertilizers, and water, contributing to effective pest control, nutrient management, and irrigation. These systems enhance efficiency, reduce labor, and promote environmentally friendly practices by minimizing chemical waste and runoff. The efficacy of a spray is largely determined by the characteristics of its droplets, including their size and velocity. These parameters are not only pivotal in assessing spray retention, i.e., how much of the spray adheres to crops versus becoming environmental runoff, but also in understanding spray drift dynamics. This study introduces a real-time deep learning-based approach for droplet detection and tracking which significantly improves the accuracy and efficiency of measuring these droplet properties. Our methodology leverages advanced AI techniques to overcome the limitations of previous tracking frameworks, employing three novel deep learning-based tracking methods. These methods are adept at handling challenges such as droplet occlusion and varying velocities, ensuring precise tracking in real-time potentially on mobile platforms. The use of a high-speed camera operating at 2000 frames per second coupled with innovative automatic annotation tools enables the creation of a large and accurately labeled droplet dataset for training and evaluation. The core of our framework lies in the ability to track droplets across frames, associating them temporally despite changes in appearance or occlusions. We utilize metrics including Multiple Object Tracking Accuracy (MOTA) and Multiple Object Tracking Precision (MOTP) to quantify the tracking algorithm’s performance. Our approach is set to pave the way for innovations in agricultural spraying systems, offering a more efficient, accurate, and environmentally responsible method of applying sprays and representing a significant step toward sustainable agricultural practices.

Knowledge graph construction in hyperbolic space for automatic image annotation

Automatic image annotation (AIA) is a fundamental and challenging task in computer vision. Considering the correlations between tags can lead to more accurate image understanding, benefiting various applications, including image retrieval and visual search. While many attempts have been made to incorporate tag correlations in annotation models, the method of constructing a knowledge graph based on external knowledge sources and hyperbolic space has not been explored. In this paper, we create an attributed knowledge graph based on vocabulary, integrate external knowledge sources such as WordNet, and utilize hyperbolic word embeddings for the tag representations. These embeddings provide a sophisticated tag representation that captures hierarchical and complex correlations more effectively, enhancing the image annotation results. In addition, leveraging external knowledge sources enhances contextuality and significantly enriches existing AIA datasets. We exploit two deep learning-based models, the Relational Graph Convolutional Network (R-GCN) and the Vision Transformer (ViT), to extract the input features. We apply two R-GCN operations to obtain word descriptors and fuse them with the extracted visual features. We evaluate the proposed approach using three public benchmark datasets. Our experimental results demonstrate that the proposed architecture achieves state-of-the-art performance across most metrics on Corel5k, ESP Game, and IAPRTC-12.

The Semantic Function of Modern Chinese “Negation + X” Modal Words Based on Communication Technology and Big Data Corpus

The semantic function of modern Chinese “negation + X” modal words based on communication technology and big data corpus has gained wide attention. As the basis of SOA architecture, Web services provide the key resources for worldwide information transfer and information sharing with their characteristics of loose coupling, platform independence, and data exchange without additional support from third-party hardware and software. However, along with the popularization and improvement of Web service technology, the number and types of Web services in the Internet are also increasing massively, and there are a large number of Web services with various functions, quality and granularity. Therefore, how to quickly and accurately discover Web services that satisfy users’ query requests from a large and complex set of services has become a critical problem to be solved in the current Web service discovery research. Based on the real corpus, this paper analyzes the similarities and differences in the semantic functions of modern Chinese “negation + X” modal words by combining lexicalization and grammatization, cognitive linguistics, systemic functional grammar and other related theories. The experimental results demonstrate that the model is designed for automatic annotation of semantic word classes, and the annotation algorithm based on the hidden horse model, combined with the Viterbi algorithm based on dynamic programming, achieves a correct rate of 94.3% in the closed test and 89.1% in the open test despite the small size of the training corpus and severe data sparsity, and the model fitting effect meets the dynamic expectations.

Identification of kidney cell types in scRNA-seq and snRNA-seq data using machine learning algorithms

IntroductionSingle-cell RNA sequencing (scRNA-seq) and single-nucleus RNA sequencing (snRNA-seq) provide valuable insights into the cellular states of kidney cells. However, the annotation of cell types often requires extensive domain expertise and time-consuming manual curation, limiting scalability and generalizability. To facilitate this process, we tested the performance of five supervised classification methods for automatic cell type annotation. ResultsWe analyzed publicly available sc/snRNA-seq datasets from five expert-annotated studies, comprising 62,120 cells from 79 kidney biopsy samples. Datasets were integrated by harmonizing cell type annotations across studies. Five different supervised machine learning algorithms (support vector machines, random forests, multilayer perceptrons, k-nearest neighbors, and extreme gradient boosting) were applied to automatically annotate cell types using four training datasets and one testing dataset. Performance metrics, including accuracy (F1 score) and rejection rates, were evaluated. All five machine learning algorithms demonstrated high accuracies, with a median F1 score of 0.94 and a median rejection rate of 1.8 %. The algorithms performed equally well across different datasets and successfully rejected cell types that were not present in the training data. However, F1 scores were lower when models trained primarily on scRNA-seq data were tested on snRNA-seq data. ConclusionsDespite limitations including the number of biopsy samples, our findings demonstrate that machine learning algorithms can accurately annotate a wide range of adult kidney cell types in scRNA-seq/snRNA-seq data. This approach has the potential to standardize cell type annotation and facilitate further research on cellular mechanisms underlying kidney disease.

Night Lighting Fault Detection Based on Improved YOLOv5

Night lighting is essential for urban life, and the occurrence of faults can significantly affect the presentation of lighting effects. Many reasons can cause lighting faults, including the damage of lamps and circuits, and the typical manifestation of the faults is that the lights do not light up. The current troubleshooting mainly relies on artificial visual inspection, making detecting faults difficult and time-consuming. Therefore, it is necessary to introduce technical means to detect lighting faults. However, current research on lighting fault detection mainly focuses on using non-visual methods such as sensor data analysis, which has the disadvantages of having a high cost and difficulty adapting to large-scale fault detection. Therefore, this study mainly focuses on solving the problem of the automatic detection of night lighting faults using machine vision methods, especially object detection methods. Based on the YOLOv5 model, two data fusion models have been developed based on the characteristics of lighting fault detection inverse problems: YOLOv5 Channel Concatenation and YOLOv5 Image Fusion. Based on the dataset obtained from the developed automatic image collection and annotation system, the training and evaluation of these three models, including the original YOLOv5, YOLOv5 Channel Concatenation, and YOLOv5 Image Fusion, have been completed. Research has found that applying complete lighting images is essential for the problem of lighting fault detection. The developed Image Fusion model can effectively fuse information and accurately detect the occurrence and area of faults, with a mAP value of 0.984. This study is expected to play an essential role in the intelligent development of urban night lighting.

Navigating the archaeal frontier: insights and projections from bioinformatic pipelines.

Archaea continues to be one of the least investigated domains of life, and in recent years, the advent of metagenomics has led to the discovery of many new lineages at the phylum level. For the majority, only automatic genomic annotations can provide information regarding their metabolic potential and role in the environment. Here, genomic data from 2,978 archaeal genomes was used to perform automatic annotations using bioinformatics tools, alongside synteny analysis. These automatic classifications were done to assess how good these different tools perform in relation to archaeal data. Our study revealed that even with lowered cutoffs, several functional models do not capture the recently discovered archaeal diversity. Moreover, our investigation revealed that a significant portion of archaeal genomes, approximately 42%, remain uncharacterized. In comparison, within 3,235 bacterial genomes, a diverse range of unclassified proteins is obtained, with well-studied organisms like Escherichia coli having a substantially lower proportion of uncharacterized regions, ranging from <5 to 25%, and less studied lineages being comparable to archaea with the range of 35-40% of unclassified regions. Leveraging this analysis, we were able to identify metabolic protein markers, thereby providing insights into the metabolism of the archaea in our dataset. Our findings underscore a substantial gap between automatic classification tools and the comprehensive mapping of archaeal metabolism. Despite advances in computational approaches, a significant portion of archaeal genomes remains unexplored, highlighting the need for extensive experimental validation in this domain, as well as more refined annotation methods. This study contributes to a better understanding of archaeal metabolism and underscores the importance of further research in elucidating the functional potential of archaeal genomes.

A deep learning-powered intelligent microdroplet analysis workflow for in-situ monitoring and evaluation of a dynamic emulsion

Accurately determining microdroplet size and uniformity in dispersed phase systems is key for assessing emulsion stability, and essential for quality monitoring and control of emulsion products. Microscopic imaging probes have provided intuitive and advanced insights for characterizing particle microscopic morphology and dispersion in multiphase flows. However, wide size distributions, edge-cutting, overlapping, and high-density target droplets can compromise the image processing accuracy, thereby affecting the precise assessment of emulsion status. In this study, we present a deep learning-based intelligent workflow for microdroplet characterization using an in-situ high-speed particle imaging probe combined with advanced image processing techniques. With the assistance of progressive automatic annotation, a droplet image database was constructed for training the Mask R-CNN model. By incorporating image patching and supervised data augmentation strategies, our well-trained model with accuracy of 95.5% can precisely detect, localize, and segment microscale droplets with various patterns. Additionally, the shape reconstruction module visualizes true shapes of overlapping and edge-cutting droplets, facilitating precise quantification of droplet size information. To validate the feasibility and generalizability of the proposed workflow, we obtained sufficient droplet images through offline sampling during emulsion processes while employing back and front illumination for in-situ monitoring. The automated method achieves precise droplet detection and size measurement, demonstrating its immense potential in online monitoring, evaluation, and control of emulsion quality.

Characterization of the carbapenem-resistant Acinetobacter baumannii clinical reference isolate BAL062 (CC2:KL58:OCL1): resistance properties and capsular polysaccharide structure.

The carbapenem-resistant Acinetobacter baumannii isolate BAL062 is a clinical reference isolate used in several recent experimental studies. It is from a ventilator-associated pneumonia (VAP) patient in an intensive care unit at the Hospital for Tropical Diseases (HTD), Ho Chi Minh City, Vietnam in 2009. Here, BAL062 was found to belong to the B sub-lineage of global clone 2 (GC2) isolates in the previously reported outbreak (2008 and 2012) of carbapenem-resistant VAP A. baumannii at the HTD. While related sub-lineage B outbreak isolates were extensively antibiotic-resistant and carry GC2-associated genomic resistance islands, AbGRI1, AbGRI2, and AbGRI3, BAL062 has lost AbGRI3 and three aminoglycoside resistance genes, armA, aacA4, and aphA1, leading to amikacin, tobramycin and kanamycin susceptibility. The location of Tn2008VAR found in the chromosome of this sub-lineage was also corrected. Like many of the outbreak isolates, BAL062 carries the KL58 gene cluster at the capsular polysaccharide (CPS) synthesis locus and an annotation key is provided. As information about K type is important for the development of novel CPS-targeting therapies, the BAL062 K58-type CPS structure was established using NMR spectroscopy. It is most closely related to K2 and K93, sharing similar configurations and linkages between K units, and contains the rare higher monosaccharide, 5,7-diacetamido-3,5,7,9-tetradeoxy-d-glycero-l-manno-non-2-ulosonic acid (5,7-di-N-acetyl-8-epipseudaminic acid; 8ePse5Ac7Ac), the 8-epimer of Pse5Ac7Ac (5,7-di-N-acetylpseudaminic acid). Inspection of publicly available A. baumannii genomes revealed a wide distribution of the KL58 locus in geographically diverse isolates belonging to several sequence types that were recovered over two decades from clinical, animal, and environmental sources.IMPORTANCEMany published experimental studies aimed at developing a clearer understanding of the pathogenicity of carbapenem-resistant Acinetobacter baumannii strains currently causing treatment failure due to extensive antibiotic resistance are undertaken using historic, laboratory-adapted isolates. However, it is ideal if not imperative that recent clinical isolates are used in such studies. The clinical reference isolate characterized here belongs to the dominant A. baumannii GC2 clone causing extensively resistant infections and has been used in various recent studies. The correlation of resistance profiles and resistance gene data is key to identifying genes available for gene knockout and complementation analyses, and we have mapped the antibiotic resistance genes to find candidates. Novel therapies, such as bacteriophage or monoclonal antibody therapies, currently under investigation as alternatives or adjuncts to antibiotic treatment to combat difficult-to-treat CRAb infections often exhibit specificity for specific structural epitopes of the capsular polysaccharide (CPS), the outer-most polysaccharide layer. Here, we have solved the structure of the CPS type found in BAL062 and other extensively resistant isolates. As consistent gene naming and annotation are important for locus identification and interpretation of experimental studies, we also have correlated automatic annotations to the standard gene names.

Crop Growth Analysis Using Automatic Annotations and Transfer Learning in Multi-Date Aerial Images and Ortho-Mosaics

Growth monitoring of crops is a crucial aspect of precision agriculture, essential for optimal yield prediction and resource allocation. Traditional crop growth monitoring methods are labor-intensive and prone to errors. This study introduces an automated segmentation pipeline utilizing multi-date aerial images and ortho-mosaics to monitor the growth of cauliflower crops (Brassica Oleracea var. Botrytis) using an object-based image analysis approach. The methodology employs YOLOv8, a Grounding Detection Transformer with Improved Denoising Anchor Boxes (DINO), and the Segment Anything Model (SAM) for automatic annotation and segmentation. The YOLOv8 model was trained using aerial image datasets, which then facilitated the training of the Grounded Segment Anything Model framework. This approach generated automatic annotations and segmentation masks, classifying crop rows for temporal monitoring and growth estimation. The study’s findings utilized a multi-modal monitoring approach to highlight the efficiency of this automated system in providing accurate crop growth analysis, promoting informed decision-making in crop management and sustainable agricultural practices. The results indicate consistent and comparable growth patterns between aerial images and ortho-mosaics, with significant periods of rapid expansion and minor fluctuations over time. The results also indicated a correlation between the time and method of observation which paves a future possibility of integration of such techniques aimed at increasing the accuracy in crop growth monitoring based on automatically derived temporal crop row segmentation masks.

VICTOR: Validation and inspection of cell type annotation through optimal regression

Single-cell RNA sequencing provides unprecedent opportunities to explore the heterogeneity and dynamics inherent in cellular biology. An essential step in the data analysis involves the automatic annotation of cells. Despite development of numerous tools for automated cell annotation, assessing the reliability of predicted annotations remains challenging, particularly for rare and unknown cell types. Here, we introduce VICTOR: Validation and inspection of cell type annotation through optimal regression. VICTOR aims to gauge the confidence of cell annotations by an elastic-net regularized regression with optimal thresholds. We demonstrated that VICTOR performed well in identifying inaccurate annotations, surpassing existing methods in diagnostic ability across various single-cell datasets, including within-platform, cross-platform, cross-studies, and cross-omics settings.

WDICD: A novel simulated dataset and structure-aware framework for semantic segmentation of spacecraft component

The identification and localization of non-cooperative target, especially for the components such as solar panel and docking ring, is crucial for missions involving the on-orbit space services, navigation, and positioning. However, on-orbit spacecraft images are difficult to obtain, and it requires substantial effort to label them with pixel-wise accuracy for semantic segmentation. To address the above problems, we construct a simulated Wide-Depth Illumination-Composite Dataset (WDICD) and introduces an automatic pixel-level semantic annotation method. Furthermore, this paper proposes a structure-aware framework for semantic segmentation of spacecraft component, which introduces a boundary-aware auxiliary task and constructs a boundary-distance-aware contrast loss based on batch-wise grouping. The related boundary-aware tasks alleviate the prediction error of semantic segmentation near the boundary. Experimental results demonstrate that the proposed method achieves SOTA mIoU results in spacecraft component segmentation against complex backgrounds on two datasets. Particularly, the test results on spaceborne device show that the proposed framework balances precision and efficiency without generating additional computational complexity.

Evaluating automatic annotation of lexicon-based models for stance detection of M-pox tweets from May 1st to Sep 5th, 2022.

Manually labeling data for supervised learning is time and energy consuming; therefore, lexicon-based models such as VADER and TextBlob are used to automatically label data. However, it is argued that automated labels do not have the accuracy required for training an efficient model. Although automated labeling is frequently used for stance detection, automated stance labels have not been properly evaluated, in the previous works. In this work, to assess the accuracy of VADER and TextBlob automated labels for stance analysis, we first manually label a Twitter, now X, dataset related to M-pox stance detection. We then fine-tune different transformer-based models on the hand-labeled M-pox dataset, and compare their accuracy before and after fine-tuning, with the accuracy of automated labeled data. Our results indicated that the fine-tuned models surpassed the accuracy of VADER and TextBlob automated labels by up to 38% and 72.5%, respectively. Topic modeling further shows that fine-tuning diminished the scope of misclassified tweets to specific sub-topics. We conclude that fine-tuning transformer models on hand-labeled data for stance detection, elevates the accuracy to a superior level that is significantly higher than automated stance detection labels. This study verifies that automated stance detection labels are not reliable for sensitive use-cases such as health-related purposes. Manually labeled data is more convenient for developing Natural Language Processing (NLP) models that study and analyze mass opinions and conversations on social media platforms, during crises such as pandemics and epidemics.