Search

PURPOSE: Meningiomas are the most common primary brain tumors in adults with management varying widely based on World Health Organization (WHO) grade. However, there are limited datasets available for researchers to develop and validate radiomic models. The purpose of our manuscript is to report on the first dataset of meningiomas in The Cancer Imaging Archive (TCIA). ACQUISITION AND VALIDATION METHODS: The dataset consists of pre-operative MRIs from 96 patients with meningiomas who underwent resection from 2010-2019 and include axial T1post and T2-FLAIR sequences-55 grade 1 and 41 grade 2. Meningioma grade was confirmed based on the 2016 WHO Bluebook classification guideline by two neuropathologists and one neuropathology fellow. The hyperintense T1post tumor and hyperintense T2-FLAIR regions were manually contoured on both sequences and resampled to an isotropic resolution of 1 × 1 × 1 mm3 . The entire dataset was reviewed by a certified medical physicist. DATA FORMAT AND USAGE NOTES: The data was imported into TCIA for storage and can be accessed at https://doi.org/10.7937/0TKV-1A36. The total size of the dataset is 8.8GB, with 47 519 individual Digital Imaging and Communications in Medicine (DICOM) files consisting of 384 image series, and 192 structures. POTENTIAL APPLICATIONS: Grade 1 and 2 meningiomas have different treatment paradigms and are often treated based on radiologic diagnosis alone. Therefore, predicting grade prior to treatment is essential in clinical decision-making. This dataset will allow researchers to create models to auto-differentiate grade 1 and 2 meningiomas as well as evaluate for other pathologic features including mitotic index, brain invasion, and atypical features. Limitations of this study are the small sample size and inclusion of only two MRI sequences. However, there are no meningioma datasets on TCIA and limited datasets elsewhere although meningiomas are the most common intracranial tumor in adults.

Objectives: This work aims to establish a dataset of ratios between tissue free water tritium (TFWT) and organically bound tritium (OBT) (containing both exchangeable and non-exchangeable OBT) in different types of seafood from Zhejiang province, China, thus to provide references for rapid screening of potential contamination of tritium in biological samples. Methods: Five types of seafood (fish, prawn, mussel, crab and kelp) were collected from Jiaxing, Ningbo, Zhoushan, Taizhou and Wenzhou city in Zhejiang Province in 2022, and measured for TFWT and OBT using tube furnace combustion system and liquid scintillation counting. Results: The observed activity concentrations of TFWT and OBT in this study were within the range of 1.01-10.09 Bq/L and 0.51-7.61 Bq/L, respectively. No significant difference in OBT/TFWT ratio was observed among different types of seafood (p > 0.05), among the geographic distribution of the five cities (p > 0.05), nor among the area of coastline, fishing ground and island (p > 0.05). Additionally, there was no significant difference in the OBT/TFWT ratio between seafood from area with and without nuclear power plant operation (p > 0.05). The mean OBT/TFWT ratio of fish, prawn, mussel, crab and kelp was 0.37 ± 0.19, 0.48 ± 0.27, 0.63 ± 0.33, 0.82 ± 0.50, and 0.64 ± 0.37, respectively. The mean and range of OBT/TFWT ratios were 0.59 ± 0.37 and 0.15-2.09 in all seafood collected from the five cities in Zhejiang Province, respectively. Conclusions: Our results indicate that tritium in seafood from coastal cities in Zhejiang Province is at the background level, and the operation of nuclear power plants in the province has no notable impact on the radioactivity levels of tritium in local marine biota. This study filled the gap in OBT/TFWT ratios in seafood, which provides new dataset for rapid detection of tritium contamination in nuclear emergencies. [ABSTRACT FROM AUTHOR]

Background: Proximal caries datasets for training artificial intelligence (AI) algorithms commonly include clinician-annotated radiographs. These conventional annotations are susceptible to observer variability, and early caries may be missed. Micro-computed tomography (CT), while not feasible in clinical applications, offers a more accurate imaging modality to support the creation of a reference-standard dataset for caries annotations. Herein, we present the Academic Center for Dentistry Amsterdam—Diagnostic Insights for Radiographic Early-caries with micro-CT (ACTA-DIRECT) dataset, which is the first dataset pairing dental radiographs and micro-CT scans to enable higher-quality annotations. Methods: The ACTA-DIRECT dataset encompasses 179 paired micro-CT scans and radiographs of early proximal carious teeth, along with three types of annotations: conventional annotations on radiographs, micro-CT-assisted annotations on radiographs, and micro-CT annotations (reference standard). Three dentists independently annotated proximal caries on radiographs, both with and without micro-CT assistance, enabling determinations of interobserver agreement and diagnostic accuracy. To establish a reference standard, one dental radiologist annotated all caries on the related micro-CT scans. Results: Micro-CT support improved interobserver agreement (Cohen's Kappa), averaging 0.64 (95% confidence interval [CI]: 0.59–0.68) versus 0.46 (95% CI: 0.44–0.48) in its absence. Likewise, average sensitivity and specificity increased from 42% (95% CI: 34–51%) to 63% (95% CI: 54–71%) and from 92% (95% CI: 88–95%) to 95% (95% CI: 92–97%), respectively. Conclusion: The ACTA-DIRECT dataset offers high-quality images and annotations to support AI-based early caries diagnostics for training and validation. This study underscores the benefits of incorporating micro-CT scans in lesion assessments, providing enhanced precision and reliability. [ABSTRACT FROM AUTHOR]

As a fundamental task of fine-grained sentiment analysis, Aspect-Category Sentiment Analysis (ACSA) aims to predict the sentiment polarities of sentences with respect to given aspect categories. Previous works on ACSA are text-based, but with the increase of multimodal user-generated content (e.g. text and image), multimodal fine-grained sentiment analysis has attracted more attention in recent years. However, most of the existing multimodal fine-grained sentiment analysis work focuses on analyzing the sentiment of aspects that explicitly exist in the textual content. And there has been rare work on multimodal sentiment analysis of implicit categories in multimodal data, due to the lack of a sufficient dataset. In this paper, we introduce a new task, named Multimodal Aspect-Category Sentiment Analysis (MACSA), with the goal of predicting sentiment polarities of image-text pairs with respect to given aspect categories. And we propose a novel Multimodal Graph-based Aligned Network (MGAM) model for this task. Our model constructs heterogeneous graphs through multimodal fine-grained information and uses a convolutional graph neural network to learn cross-modal fine-grained interaction. We provide a new multimodal aspect category sentiment dataset, named the Hotel-MACSA dataset to evaluate our model, which contains multimodal fine-grained aligned annotations. The experimental results demonstrate the effectiveness of our proposed MGAM model for this new task. The MGAM model achieves an accuracy of 86.06% on the Hotel-MACSA dataset and 75.25% on the hard version test dataset, outperforming all baseline models. [ABSTRACT FROM AUTHOR]

Drivable Area (DA) detection is crucial for autonomous driving. Camera-based methods rely heavily on illumination conditions and often fail to capture accurate 3D information, while LiDAR-based methods offer accurate 3D data and are less susceptible to illumination conditions. However, existing LiDAR-based methods focus on point-wise detection, so are prone to occlusion and limited by point cloud sparsity, which leads to decreased performance in motion planning and localization. We propose Argoverse-grid, a grid-wise DA detection dataset derived from Argoverse 1, comprising over 20K frames with fine-grained BEV DA labels across various scenarios. We also introduce Grid-DATrNet, a first grid-wise DA detection model utilizing global attention through transformers. Our experiments demonstrate the superiority of Grid-DATrNet over various methods, including both LiDAR and camera-based approaches, in detecting grid-wise DA on the proposed Argoverse-grid dataset. Grid-DATrNet achieves state-of-the-art results with an accuracy of 93.28% and an F1-score of 0.8328. We show that Grid-DATrNet can detect grids even in occluded and unmeasured areas by leveraging contextual and semantic information through global attention, unlike CNN-based DA detection methods. The preprocessing code for Argoverse-grid, experiment code, Grid-DATrNet implementation, and result visualization code are available at AVE Laboratory official git hub. [ABSTRACT FROM AUTHOR]

Electric bicycle datasets for lift control have played a crucial role in the development of electric bicycle lift entry detection algorithms. However, existing datasets often encounter issues, including a small dataset size, a high false detection rate, and the absence of a publicly available benchmark dataset. This paper addresses these challenges by constructing a new electric bicycle detection dataset for lift control based on the research demands of the electric bicycle detection task for lift control. XHNet_EB, a car scene image dataset covering various types of electric bicycles, was constructed based on images taken by a camera from above. Segmented annotation was employed, framing the front and rear of the electric bicycle independently. This approach effectively addressed the problems of many irrelevant features and a high false detection rate caused by the use of whole-electric-bicycle annotations in mainstream datasets. AP_50, AP_75, the mAP, and the number of false detections in the images were used for quantitative analysis of the dataset. The experimental results indicated that the object detection accuracy of the XHNet_EB dataset was excellent. Quantitative analysis and evaluation of the number of false detections in images were conducted using four mainstream lightweight detection model algorithms. The results demonstrated that segmented annotation reduced the false detection rate more effectively than entire electric bicycle annotation. This study identified drawbacks in existing datasets. The dataset proposed in this paper overcomes the shortcomings of existing commercial data and solves problems such as the high false detection rate caused by the inclusion of many irrelevant features caused by the "whole-electric-bicycle annotation" method, which could help with the development of electric bicycle detection applications in lifts. [ABSTRACT FROM AUTHOR]

In computer vision, object detection is the classical and most challenging problem to get accurate results in detecting objects. With the significant advancement of deep learning techniques over the past decades, most researchers work on enhancing object detection, segmentation and classification. Object detection performance is measured in both detection accuracy and inference time. The detection accuracy in two stage detectors is better than single stage detectors. In 2015, the real-time object detection system YOLO was published, and it rapidly grew its iterations, with the newest release, YOLOv8 in January 2023. The YOLO achieves a high detection accuracy and inference time with single stage detector. Many applications easily adopt YOLO versions due to their high inference speed. This paper presents a complete survey of YOLO versions up to YOLOv8. This article begins with explained about the performance metrics used in object detection, post-processing methods, dataset availability and object detection techniques that are used mostly; then discusses the architectural design of each YOLO version. Finally, the diverse range of YOLO versions was discussed by highlighting their contributions to various applications. [ABSTRACT FROM AUTHOR]

This work presents a microwave resonant multi-parameter sensor devoted to the simultaneous extraction of three characteristics of a homogeneous solid sample: its dielectric permittivity, its loss tangent and its thickness. The device is composed of three coupled resonators in two different substrate boards, having the sample between the boards, in a sandwich configuration. Presence of the sample impacts the electrical response of the device, not only influencing resonators, but also by affecting inter-resonator couplings. A method to analyse the response of the device, allowing for the extraction of the desired characteristics of the sample is proposed, as well as an experimental calibration procedure. The model is built upon 990 simulations, calibrated with three reference-samples measurements and then tested over 18 experimental measurements, with good results, thereby validating the multi-parameter sensing approach. [ABSTRACT FROM AUTHOR]

Improvements in analytical technique and data processing lead to a large deposit of detrital zircon U–Pb and Hf isotopic data in published journal articles, thesis and reports. With the support of Deep‐time Digital Earth Big Science Program, OneSediment Project conducted a team‐working effort to assemble the detrital zircon U–Pb and Hf isotopic data for mainland China and adjacent regions. Entity‐relationship diagram was constructed for detrital zircon data to determine what information need to be collected. Researchers and students from 13 institutions were organized together to fulfil this task and generated 13 detrital zircon datasets. The assembled datasets totally include 6635 samples and 560,596 analyses. The samples were checked in terms of lithology and stratigraphy according to the latest stratigraphic framework. Collected detrital zircon U–Pb and Hf isotopic data were recalculated for the best U–Pb age and εHf(t) values. They can be used to track crustal growth, tectonic evolution, provenance analysis and palaeogeographical change in regional and, when combined with other dataset, global scales. [ABSTRACT FROM AUTHOR]

Place recognition is crucial for robot localization and loop closure in simultaneous localization and mapping (SLAM). Light Detection and Ranging (LiDAR), known for its robust sensing capabilities and measurement consistency even in varying illumination conditions, has become pivotal in various fields, surpassing traditional imaging sensors in certain applications. Among various types of LiDAR, spinning LiDARs are widely used, while non-repetitive scanning patterns have recently been utilized in robotics applications. Some LiDARs provide additional measurements such as reflectivity, Near Infrared (NIR), and velocity from Frequency modulated continuous wave (FMCW) LiDARs. Despite these advances, there is a lack of comprehensive datasets reflecting the broad spectrum of LiDAR configurations for place recognition. To tackle this issue, our paper proposes the HeLiPR dataset, curated especially for place recognition with heterogeneous LiDARs, embodying spatiotemporal variations. To the best of our knowledge, the HeLiPR dataset is the first heterogeneous LiDAR dataset supporting inter-LiDAR place recognition with both non-repetitive and spinning LiDARs, accommodating different field of view (FOV)s and varying numbers of rays. The dataset covers diverse environments, from urban cityscapes to high-dynamic freeways, over a month, enhancing adaptability and robustness across scenarios. Notably, HeLiPR dataset includes trajectories parallel to MulRan sequences, making it valuable for research in heterogeneous LiDAR place recognition and long-term studies. The dataset is accessible at https://sites.google.com/view/heliprdataset. [ABSTRACT FROM AUTHOR]

This paper presents a unique outdoor aerial visual-inertial-LiDAR dataset captured using a multi-sensor payload to promote the global navigation satellite system (GNSS)-denied navigation research. The dataset features flight distances ranging from 300 m to 5 km, collected using a DJI-M600 hexacopter drone and the National Research Council (NRC) Bell412 Advanced Systems Research Aircraft (ASRA). The dataset consists of hardware-synchronized monocular images, inertial measurement unit (IMU) measurements, 3D light detection and ranging (LiDAR) point-clouds, and high-precision real-time kinematic (RTK)-GNSS based ground truth. Nine data sequences were collected as robot operating system (ROS) bags over 100 mins of outdoor environment footage ranging from urban areas, highways, airports, hillsides, prairies, and waterfronts. The dataset was collected to facilitate the development of visual-inertial-LiDAR odometry and mapping algorithms, visual-inertial navigation algorithms, object detection, segmentation, and landing zone detection algorithms based on real-world drone and full-scale helicopter data. All the data sequences contain raw sensor measurements, hardware timestamps, and spatio-temporally aligned ground truth. The intrinsic and extrinsic calibrations of the sensors are also provided, along with raw calibration datasets. A performance summary of state-of-the-art methods applied on the data sequences is also provided. [ABSTRACT FROM AUTHOR]

Many sensitive applications require that data remain confidential and undisclosed, even for intrusion detection objectives. For this purpose, the detection of anomalies in encrypted data has become increasingly vital. Deep learning models are becoming good tools to detect anomalies in encrypted data without the need to pass through data decryption. This paper presents a systematic review focusing on the advancements made in deep learning models for intrusion detection over encrypted data with privacy preservation. This study aims to guide researchers on how to select the right tools to set up an intrusion detection system over encrypted data with privacy preservation. The study presented the context and challenges of intrusion detection on encrypted data and how machine learning-based solutions can circumvent these challenges. The paper looks at recently proposed solutions, examines metrics for assessing model performance, and evaluates frequently used reference datasets. Deep learning models are also evaluated with statistics on the most frequent models, datasets, and encryption tools. The performance metrics of the studied solutions are investigated as a function of the encryption tools, the deployed deep learning models, the privacy preservation tools, the deployed datasets, and the eventual additional tools and algorithms. Our recommendations help researchers evaluate their proposals for preserving privacy and detecting intrusions on encrypted data using deep learning techniques. [ABSTRACT FROM AUTHOR]

EMOKINE is a software package and dataset creation suite for emotional full-body movement research in experimental psychology, affective neuroscience, and computer vision. A computational framework, comprehensive instructions, a pilot dataset, observer ratings, and kinematic feature extraction code are provided to facilitate future dataset creations at scale. In addition, the EMOKINE framework outlines how complex sequences of movements may advance emotion research. Traditionally, often emotional-'action'-based stimuli are used in such research, like hand-waving or walking motions. Here instead, a pilot dataset is provided with short dance choreographies, repeated several times by a dancer who expressed different emotional intentions at each repetition: anger, contentment, fear, joy, neutrality, and sadness. The dataset was simultaneously filmed professionally, and recorded using XSENS® motion capture technology (17 sensors, 240 frames/second). Thirty-two statistics from 12 kinematic features were extracted offline, for the first time in one single dataset: speed, acceleration, angular speed, angular acceleration, limb contraction, distance to center of mass, quantity of motion, dimensionless jerk (integral), head angle (with regards to vertical axis and to back), and space (convex hull 2D and 3D). Average, median absolute deviation (MAD), and maximum value were computed as applicable. The EMOKINE software is appliable to other motion-capture systems and is openly available on the Zenodo Repository. Releases on GitHub include: (i) the code to extract the 32 statistics, (ii) a rigging plugin for Python for MVNX file-conversion to Blender format (MVNX=output file XSENS® system), and (iii) a Python-script-powered custom software to assist with blurring faces; latter two under GPLv3 licenses. [ABSTRACT FROM AUTHOR]

Background: The document presents an extensive set of data on the occurrence of Neuroptera and Raphidioptera in some regions of European Russia. The results of our own research, as well as scientific collections, have been processed. The data were collected in 17 regions. In our own research, we used different ways to obtain information, which allowed us to collect extensive material for the dataset. This dataset provides valuable information about the biodiversity of Neuroptera and Raphidioptera, the abundance of each taxon collected and the time of taxon collections. New information: Our dataset contains up-to-date information on the occurrence of Neuroptera and Raphidioptera in the Volga River and Don River Basins located in the Russian Plain of European Russia (17 regions of European Russia). The dataset consists of 4,826 occurrence records. All of them are georeferenced (17,373 individuals were studied). A total of 83 species of Neuroptera (8 families, 36 genera) and four species of Raphidioptera (2 families, 4 genera) were recorded within the investigated area. [ABSTRACT FROM AUTHOR]

Progress in automatic sign language recognition and translation has been hindered by the scarcity of datasets available for the training of machine learning algorithms, a challenge that is even more acute for languages with smaller signing communities, such as Spanish. In this paper, we introduce a dataset of 300 isolated signs in Spanish Sign Language, collected online via a web application with contributions from 124 participants, resulting in a total of 8000 instances. This dataset, which is openly available, includes keypoints extracted using MediaPipe Holistic. The goal of this paper is to describe the construction and characteristics of the dataset and to provide a baseline classification method using a spatial–temporal graph convolutional network (ST-GCN) model, encouraging the scientific community to improve upon it. The experimental section offers a comparative analysis of the method's performance on the new dataset, as well as on two other well-known datasets. The dataset, code, and web app used for data collection are freely available, and the web app can also be used to test classifier performance on-line in real-time. [ABSTRACT FROM AUTHOR]

Food image recognition is essential for developing an elderly-friendly daily food recording application in Indonesia. However, existing datasets and models are limited and do not cover the diversity and complexity of Indonesian food. In this paper, we present a new dataset of 24,427 images of 160 types of Indonesian food with higher variety and quality than previous datasets. We also train and compare the performance of 67 models based on 16 state-of-the-art deep learning architectures on this dataset. We find that efficientnet_v2_l provides the best accuracy of 85.44%, followed by other models such as convnext_large and swin_s. We also discuss the trade-off between model size and performance, as well as the challenges and limitations of food image classification. Our dataset and models can serve as a basis for developing a user-friendly and accurate food recording application for the elderly population in Indonesia. [ABSTRACT FROM AUTHOR]

This document discusses a new database that contains 520 studies on the carcinogenicity data of 238 pharmaceuticals across 14 ATC classifications. The database includes non-clinical animal studies and human information for approved drugs, and can be used for correlation and concordance analyses. It provides insights into the tumorigenic potential of structural analogues and includes information on species, strain sensitivities, and affected organs/tissues. The authors emphasize the importance of repeat-dose toxicity studies in identifying potential concerns regarding tumorigenic potential. The database also includes information on the incidence and severity of effects observed in these studies, such as hyperplasia and neoplastic changes, which are relevant in assessing the carcinogenicity of pharmaceuticals. [Extracted from the article]

The identification of gas leakages is a significant factor to be taken into consideration in various industries such as coal mines, chemical industries, etc., as well as in residential applications. In order to reduce damage to the environment as well as human lives, early detection and gas type identification are necessary. The main focus of this paper is multimodal gas data that were obtained simultaneously by using multiple sensors for gas detection and a thermal imaging camera. As the reliability and sensitivity of low-cost sensors are less, they are not suitable for gas detection over long distances. In order to overcome the drawbacks of relying just on sensors to identify gases, a thermal camera capable of detecting temperature changes is also used in the collection of the current multimodal dataset The multimodal dataset comprises 6400 samples, including smoke, perfume, a combination of both, and neutral environments. In this paper, convolutional neural networks (CNNs) are trained on thermal image data, utilizing variants such as bidirectional long–short-term memory (Bi-LSTM), dense LSTM, and a fusion of both datasets to effectively classify comma separated value (CSV) data from gas sensors. The dataset can be used as a valuable source for research scholars and system developers to improvise their artificial intelligence (AI) models used for gas leakage detection. Furthermore, in order to ensure the privacy of the client's data, this paper explores the implementation of federated learning for privacy-protected gas leakage classification, demonstrating comparable accuracy to traditional deep learning approaches. [ABSTRACT FROM AUTHOR]

Three-dimensional dense reconstruction involves extracting the full shape and texture details of three-dimensional objects from two-dimensional images. Although 3D reconstruction is a crucial and well-researched area, it remains an unsolved challenge in dynamic or complex environments. This work provides a comprehensive overview of classical 3D dense reconstruction techniques, including those based on geometric and optical models, as well as approaches leveraging deep learning. It also discusses the datasets used for deep learning and evaluates the performance and the strengths and limitations of deep learning methods on these datasets. [ABSTRACT FROM AUTHOR]

Writing is a commonplace activity that individuals partake in regularly. However, the implications behind it are often overlooked. When we write, various psychological factors come into play as the pen creates letters on the paper. Handwriting analysis has long been a subject of study, attracting researchers from diverse disciplines such as graphology, psychology, paleography, neuroscience, criminology, and computer science. Among the promising applications of handwriting analysis is gender classification, where a system can predict the gender of a writer based on their handwriting style. Since each individual's handwriting is unique, and variations exist between the handwriting of different genders, an automatic gender classification system can exploit these differences to make predictions. This paper presents a deep-learning-based gender classification system specifically designed for Urdu handwriting. The proposed approach utilizes a CNN network trained and tested on a self-created dataset contributed by 200 distinct male and 200 female Urdu writers. Through this method, the gender classification system achieved an impressive overall accuracy of 99.63%. The results obtained demonstrate that our technique for Urdu handwriting-based writer identification surpasses existing approaches. In the future, we intend to explore transfer learning techniques to further advance this field. [ABSTRACT FROM AUTHOR]

Aiming at the problems of poor image recognition robustness and poor model generalization in camouflaged object segmentation, inspired by the receptive field structure of the human visual system in neuroscience, this paper proposed a polarization imaging camouflage target detection method based on the receptive field network of focused attention. According to the polarization imaging target detection needs, it constructed the polarization imaging dataset that could effectively contain the background noise as well as obtain the detailed features of the target. The proposed method based on the recognition and localization network framework, which could effectively improve the discriminability and robustness of camouflaged target features by improving the feature extraction module and the decoder module, which exploited the relationship between the eccentricity and the size of the receptive field to cover multi-scale target information. The experimental validation carries out using a self- constructed dataset on multiple typical targets and comparing the subjective visual and objective evaluation metrics of the segmentation results with classical algorithms, and the results of the ablation experiments validate the effectiveness of the present segmentation method. [ABSTRACT FROM AUTHOR]

Background and Objectives: Current national or regional guidelines for the pathology reporting on invasive breast cancer differ in certain aspects, resulting in divergent reporting practice and a lack of comparability of data. Here we report on a new international dataset for the pathology reporting of resection specimens with invasive cancer of the breast. The dataset was produced under the auspices of the International Collaboration on Cancer Reporting (ICCR), a global alliance of major (inter‐)national pathology and cancer organizations. Methods and Results: The established ICCR process for dataset development was followed. An international expert panel consisting of breast pathologists, a surgeon, and an oncologist prepared a draft set of core and noncore data items based on a critical review and discussion of current evidence. Commentary was provided for each data item to explain the rationale for selecting it as a core or noncore element, its clinical relevance, and to highlight potential areas of disagreement or lack of evidence, in which case a consensus position was formulated. Following international public consultation, the document was finalized and ratified, and the dataset, which includes a synoptic reporting guide, was published on the ICCR website. Conclusions: This first international dataset for invasive cancer of the breast is intended to promote high‐quality, standardized pathology reporting. Its widespread adoption will improve consistency of reporting, facilitate multidisciplinary communication, and enhance comparability of data, all of which will help to improve the management of invasive breast cancer patients. [ABSTRACT FROM AUTHOR]

The stable hydrogen isotope in precipitation is an effective environmental tracer for climatic and hydrologic studies. However, accurate and high-precision precipitation hydrogen isoscapes are currently unavailable in China. In this study, a data fusion method based on Convolutional Neural Networks (CNN) is used to fuse the hydrogen isotopic composition (δ2Hp) of observations and isotope-equipped general circulation model (iGCM) simulations. A precipitation hydrogen isoscape with a temporal resolution of monthly and a spatial resolution of 50–60 km is established for East China for the 1969–2017 period. Prior to building the isoscape, the performance of three data fusion methods (DFMs) and two bias correction methods (BCMs) is compared. The results indicate that the CNN fusion method performs the best with a correlation coefficient larger than 0.90 and root mean square error smaller than 10.5‰when using observation as a benchmark. The fusion methods based on back propagation and long short-term memory neural network perform similarly, while slightly outperforming the bias correction methods. Thus, the CNN method is used to generate the hydrogen isoscape, and the temporal and spatial distribution characteristics of the hydrogen isotope in precipitation are analyzed based on this dataset. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ2Hp is consistent with the temperature effect in northern China, and consistent with the precipitation amount effect in southern China. The trend of the δ2Hp time series is consistent with that of observed precipitation and temperature. Overall, the generated isoscape effectively reproduces the observations, and has the characteristics of time continuity and relative spatial regularity, which can provide valuable data support for tracking atmospheric and hydrological processes. [ABSTRACT FROM AUTHOR]

Correct and robust ego-lane index estimation is crucial for autonomous driving in the absence of high-definition maps, especially in urban environments. Previous ego-lane index estimation approaches rely on feature extraction, which limits the robustness. To overcome these shortages, this study proposes a robust ego-lane index estimation framework upon only the original visual image. After optimization of the processing route, the raw image was randomly cropped in the height direction and then input into a double supervised LaneLoc network to obtain the index estimations and confidences. A post-process was also proposed to achieve the global ego-lane index from the estimated left and right indexes with the total lane number. To evaluate our proposed method, we manually annotated the ego-lane index of public datasets which can work as an ego-lane index estimation baseline for the first time. The proposed algorithm achieved 96.48/95.40% (precision/recall) on the CULane dataset and 99.45/99.49% (precision/recall) on the TuSimple dataset, demonstrating the effectiveness and efficiency of lane localization in diverse driving environments. The code and dataset annotation results will be exposed publicly on . [ABSTRACT FROM AUTHOR]

Event extraction (EE) is capable of providing essential information to facilitate comprehension of legal cases by identifying event types and extracting corresponding arguments from legal case documents. In the legal field, events are often presented in the form of document, with arguments scattered across multiple sentences, which means that legal EE at the document level is needed to better capture the complete event. However, the existing legal EE datasets mainly focused on event extraction at the sentence level, with little attention given to the document level. Obviously, it put the development of document-level event extraction (DEE) in the legal field at a disadvantage. To address this challenge, we proposed DLEE, the first DEE dataset in the legal field with two distinctive features: (1) Document-level Semi-automated Annotation, ensuring effective annotation with high quality. (2) Large-scale and Fine-grained coverage, comprising 10,014 events and 99,423 arguments. Finally, we assessed the performance of commonly used DEE baseline models on DLEE. It revealed that the DLEE is an open question, and further attention is needed for the improvement of the models' performance. [ABSTRACT FROM AUTHOR]

Traditional methods for object detection typically necessitate a substantial amount of training data, and creating high-quality training data is time-consuming. We propose a novel Few-Shot Object Detection network (FSODv2) in this paper that aims to detect objects from previously unseen categories using only a few annotated examples. Attention RPN, Multi-Relation Detector, and Contrastive Training strategy are central to our method (Fan et al., in: CVPR, 2020), which exploit similarity between few shot support set and query set to detect novel objects while suppressing false detection in the background. We also contribute a new dataset, FSOD-1k, which contains 1000 categories of various objects with high-quality annotations to train our network. To the best of our knowledge, this is one of the first datasets designed for few-shot object detection. This paper improves our FSOD model through well-designed model calibration in three areas: (1) we propose an improved FPN with multi-scale support inputs to calibrate the multi-scale support-query feature matching by exploiting multi-scale features from the same support image with different input scales; (2) we introduce a support classification supervision branch to calibrate the support feature supervision, aligning to the query feature training supervision; (3) we propose backbone calibration to preserve prior knowledge while alleviating backbone bias toward base classes by employing classification dataset to help our model calibration procedure, where such dataset has previously only been used for pre-training in other related works. Besides, we propose a Fast Attention RPN to improve evaluation speed and save computational memory during inference. Once trained, our few-shot network can detect objects from previously unseen categories without further training or fine-tuning, resulting in new state-of-the-art performance on different datasets in the few-shot setting. Our method is general in scope and has numerous potential applications. The dataset link is https://github.com/fanq15/Few-Shot-Object-Detection-Dataset. [ABSTRACT FROM AUTHOR]

Research on language and cognition relies extensively on psycholinguistic datasets or "norms". These datasets contain judgments of lexical properties like concreteness and age of acquisition, and can be used to norm experimental stimuli, discover empirical relationships in the lexicon, and stress-test computational models. However, collecting human judgments at scale is both time-consuming and expensive. This issue of scale is compounded for multi-dimensional norms and those incorporating context. The current work asks whether large language models (LLMs) can be leveraged to augment the creation of large, psycholinguistic datasets in English. I use GPT-4 to collect multiple kinds of semantic judgments (e.g., word similarity, contextualized sensorimotor associations, iconicity) for English words and compare these judgments against the human "gold standard". For each dataset, I find that GPT-4's judgments are positively correlated with human judgments, in some cases rivaling or even exceeding the average inter-annotator agreement displayed by humans. I then identify several ways in which LLM-generated norms differ from human-generated norms systematically. I also perform several "substitution analyses", which demonstrate that replacing human-generated norms with LLM-generated norms in a statistical model does not change the sign of parameter estimates (though in select cases, there are significant changes to their magnitude). I conclude by discussing the considerations and limitations associated with LLM-generated norms in general, including concerns of data contamination, the choice of LLM, external validity, construct validity, and data quality. Additionally, all of GPT-4's judgments (over 30,000 in total) are made available online for further analysis. [ABSTRACT FROM AUTHOR]

Background: The south of Benin, a country in West Africa, is still home to remnants of dense forests that benefit from a particularly rainy sub-equatorial climate, with annual rainfall of up to 1,200 mm. These forest ecosystems are an integral part of the West African forest block, which stretches from Liberia to Togo. However, despite their richness and ecological importance, these forests are unfortunately subject to strong human pressures, particularly from slash-and-burn agriculture, intensive logging and the growing urbanisation of coastal areas. Preserving these forests is crucial, however, as they are home to remarkable plant and animal biodiversity, with many endemic species. What's more, these forests play an essential role in regulating the local climate, protecting soil and water resources, as well as providing local populations with a vital source of energy wood, non-timber forest products and support for their traditional agricultural practices. Faced with these conservation challenges, identifying and characterising the main tree species found in the forests of southern and central Benin, forest species and their ecology is an essential prerequisite for implementing sustainable management and restoration strategies for these threatened forest ecosystems in southern Benin. This work aims to identify and draw attention to the different forest species, specially tree forest species present in southern and central Benin. New information: The dataset provides information on forest species found in southern and central Benin, West Africa. This dataset is extremely useful for forestry research, as it focuses mainly on the various forest species of major importance. It can be used as a basis for characterising individuals or populations of species, based on their abundance in relation to anthropogenic pressure and changes in environmental conditions. These species are characteristic of forests and, above all, are of particular interest both to populations and to managers of protected areas. Field collections were initiated in 2007 as part of natural forest inventory work. The data collected have been completed by various field works that followed this work on forest species in southern Benin. The latest version of the dataset is publicly and freely accessible on the GBIF website at the address . It should be noted that the fact that the collection and monitoring were carried out in southern Benin, a region known for its great diversity of species, over a period of 10 years making these data particularly relevant information to study the effects of climate change and human pressure on ecosystems in this area. [ABSTRACT FROM AUTHOR]

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The paper addresses data generation methods for training neural network models and solving problems of argument mining. Data preparation includes the creation of an annotated corpus and the generation of a dataset for a specific task and the selected training model. Corpora annotated manually by experts can be augmented with synthetic text data derived from paraphrasing or back-translating the texts of the base corpus. A specific feature of the task of generating a dataset is the need to identify components in the text and indicate their role in the argument (premise, thesis, counterargument). The role of argumentation indicators in the problem of data preparation is discussed and a statistical study of the information content of indicators on the prepared ArgNet corpus is carried out. [ABSTRACT FROM AUTHOR]

Automated sandbox-based analysis systems are dominantly focused on sequences of API calls, which are widely acknowledged as discriminative and easily extracted features. In this paper, we argue that an extension of the feature set beyond API calls may improve the malware detection performance. For this purpose, we apply the Cuckoo open-source sandbox system, carefully configured for the production of a novel dataset for dynamic malware analysis containing 22,200 annotated samples (11,735 benign and 10,465 malware). Each sample represents a full-featured report generated by the Cuckoo sandbox when a corresponding binary file is submitted for analysis. To support our position that the discriminative power of the full-featured sandbox reports is greater than the discriminative power of just API call sequences, we consider samples obtained from binary files whose execution induced API calls. In addition, we derive an additional dataset from samples in the full-featured dataset, whose samples contain only information on API calls. In a three-way factorial design experiment (considering the feature set, the feature representation technique, and the random forest model hyperparameter settings), we trained and tested a set of random forest models in a two-class classification task. The obtained results demonstrate that resorting to full-featured sandbox reports improves malware detection performance. The accuracy of 95.56 percent obtained for API call sequences was increased to 99.74 percent when full-featured sandbox reports were considered. [ABSTRACT FROM AUTHOR]

Traditional road testing of autonomous vehicles faces significant limitations, including long testing cycles, high costs, and substantial risks. Consequently, autonomous driving simulators and dataset-based testing methods have gained attention for their efficiency, low cost, and reduced risk. Simulators can efficiently test extreme scenarios and provide quick feedback, while datasets offer valuable real-world driving data for algorithm training and optimization. However, existing research often provides brief and limited overviews of simulators and datasets. Additionally, while the role of virtual autonomous driving competitions in advancing autonomous driving technology is recognized, comprehensive surveys on these competitions are scarce. This survey paper addresses these gaps by presenting an in-depth analysis of 22 mainstream autonomous driving simulators, focusing on their accessibility, physics engines, and rendering engines. It also compiles 35 open-source datasets, detailing key features in scenes and data-collecting sensors. Furthermore, the paper surveys 10 notable virtual competitions, highlighting essential information on the involved simulators, datasets, and tested scenarios involved. Additionally, this review analyzes the challenges in developing autonomous driving simulators, datasets, and virtual competitions. The aim is to provide researchers with a comprehensive perspective, aiding in the selection of suitable tools and resources to advance autonomous driving technology and its commercial implementation. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Xinjiang University (Natural Science Edition) is the property of Xinjiang University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Fashion image captioning is a critical task in the fashion industry that aims to automatically generate product descriptions for fashion items. However, existing fashion image captioning models predict a fixed caption for a particular fashion item once deployed, which does not cater to unique preferences. We explore a controllable way of fashion image captioning that allows the users to specify a few semantic attributes to guide the caption generation. Our approach utilizes semantic attributes as a control signal, giving users the ability to specify particular fashion attributes (e.g., stitch, knit, sleeve) and styles (e.g., cool, classic, fresh) that they want the model to incorporate when generating captions. By providing this level of customization, our approach creates more personalized and targeted captions that suit individual preferences. To evaluate the effectiveness of our proposed approach, we clean, filter, and assemble a new fashion image caption dataset called FACAD170K from the current FACAD dataset. This dataset facilitates learning and enables us to investigate the effectiveness of our approach. Our results demonstrate that our proposed approach outperforms existing fashion image captioning models as well as conventional captioning methods. Besides, we further validate the effectiveness of the proposed method on the MSCOCO and Flickr30K captioning datasets and achieve competitive performance. [ABSTRACT FROM AUTHOR]

This work presents an electrical measurement dataset from a split-system air conditioner in normal operating conditions and with specific faults, such as incrustation in the condenser and evaporator air inlet with different levels of blocking, which often occurs in this type of equipment. We also added compressor capacitor degradation, which is a very common fault in this type of equipment, although it is scarcely addressed in research. The data were obtained through a non-invasive current sensor and a grain-oriented voltage sensor containing the values of the current and voltage of equipment that was installed in the field and tested at different levels for these fault conditions. This work not only explains how the entire data collection process was carried out but also presents two examples of fast Fourier transform (FFT) applications for the detection and diagnosis of faults through the electrical measurements analyzed in our studies, which had good effectiveness. Dataset: The dataset has been submitted as a Supplementary File. Dataset License: CC-BY-NC [ABSTRACT FROM AUTHOR]

Abstract Background Proximal caries datasets for training artificial intelligence (AI) algorithms commonly include clinician-annotated radiographs. These conventional annotations are susceptible to observer variability, and early caries may be missed. Micro-computed tomography (CT), while not feasible in clinical applications, offers a more accurate imaging modality to support the creation of a reference-standard dataset for caries annotations. Herein, we present the Academic Center for Dentistry Amsterdam—Diagnostic Insights for Radiographic Early-caries with micro-CT (ACTA-DIRECT) dataset, which is the first dataset pairing dental radiographs and micro-CT scans to enable higher-quality annotations. Methods The ACTA-DIRECT dataset encompasses 179 paired micro-CT scans and radiographs of early proximal carious teeth, along with three types of annotations: conventional annotations on radiographs, micro-CT-assisted annotations on radiographs, and micro-CT annotations (reference standard). Three dentists independently annotated proximal caries on radiographs, both with and without micro-CT assistance, enabling determinations of interobserver agreement and diagnostic accuracy. To establish a reference standard, one dental radiologist annotated all caries on the related micro-CT scans. Results Micro-CT support improved interobserver agreement (Cohen’s Kappa), averaging 0.64 (95% confidence interval [CI]: 0.59–0.68) versus 0.46 (95% CI: 0.44–0.48) in its absence. Likewise, average sensitivity and specificity increased from 42% (95% CI: 34–51%) to 63% (95% CI: 54–71%) and from 92% (95% CI: 88–95%) to 95% (95% CI: 92–97%), respectively. Conclusion The ACTA-DIRECT dataset offers high-quality images and annotations to support AI-based early caries diagnostics for training and validation. This study underscores the benefits of incorporating micro-CT scans in lesion assessments, providing enhanced precision and reliability. Graphical Abstract

The document presents an extensive set of data on the occurrence of Neuroptera and Raphidioptera in some regions of European Russia. The results of our own research, as well as scientific collections, have been processed. The data were collected in 17 regions. In our own research, we used different ways to obtain information, which allowed us to collect extensive material for the dataset. This dataset provides valuable information about the biodiversity of Neuroptera and Raphidioptera, the abundance of each taxon collected and the time of taxon collections.Our dataset contains up-to-date information on the occurrence of Neuroptera and Raphidioptera in the Volga River and Don River Basins located in the Russian Plain of European Russia (17 regions of European Russia). The dataset consists of 4,826 occurrence records. All of them are georeferenced (17,373 individuals were studied). A total of 83 species of Neuroptera (8 families, 36 genera) and four species of Raphidioptera (2 families, 4 genera) were recorded within the investigated area.

Objective. The goal is to develop a web service for detecting aerial objects that detects a flying object, highlights it in an image and classifies it as a threat, since modern aerial object detection systems do not always cope with the task of detecting unmanned aerial vehicles due to their small size, low flight altitude and the use of materials that are barely noticeable to radar stations. Unmanned aerial vehicles that operate without operator control make it difficult to detect by radio signals. To detect UAVs, it is proposed to use a system based on optical scanning of the sky around protected objects. The system should be capable of autonomous operation and include aerial object detectors created on the basis of computer vision and artificial intelligence technologies. Method. The research and development of the airspace monitoring web service are based on the methods of system analysis, synthesis, and deduction. Result. The visual part of the web interface has been designed and developed; a dataset has been formed from open sources for the correct detection of flying objects; a neural network detector has been developed for classifying flying objects that pose a danger; a software module has been developed that allows for the automatic detection of identification flags of dangerous air objects with subsequent provision of reports in txt files in yolo format (coordinates are normalized). Conclusion. Separation of the visual part of the service will allow for distributed deployment of the server part, increasing flexibility and scalability. Development of the administrator control panel will allow for effective control of the service, management of settings and users. As a result, the web service will be able to: monitor the sky around protected objects, automatically detecting and classifying air objects and identifying air objects by threat level, providing information for taking necessary measures.

Abstract Improvements in analytical technique and data processing lead to a large deposit of detrital zircon U–Pb and Hf isotopic data in published journal articles, thesis and reports. With the support of Deep‐time Digital Earth Big Science Program, OneSediment Project conducted a team‐working effort to assemble the detrital zircon U–Pb and Hf isotopic data for mainland China and adjacent regions. Entity‐relationship diagram was constructed for detrital zircon data to determine what information need to be collected. Researchers and students from 13 institutions were organized together to fulfil this task and generated 13 detrital zircon datasets. The assembled datasets totally include 6635 samples and 560,596 analyses. The samples were checked in terms of lithology and stratigraphy according to the latest stratigraphic framework. Collected detrital zircon U–Pb and Hf isotopic data were recalculated for the best U–Pb age and εHf(t) values. They can be used to track crustal growth, tectonic evolution, provenance analysis and palaeogeographical change in regional and, when combined with other dataset, global scales.

Abstract This work presents a microwave resonant multi-parameter sensor devoted to the simultaneous extraction of three characteristics of a homogeneous solid sample: its dielectric permittivity, its loss tangent and its thickness. The device is composed of three coupled resonators in two different substrate boards, having the sample between the boards, in a sandwich configuration. Presence of the sample impacts the electrical response of the device, not only influencing resonators, but also by affecting inter-resonator couplings. A method to analyse the response of the device, allowing for the extraction of the desired characteristics of the sample is proposed, as well as an experimental calibration procedure. The model is built upon 990 simulations, calibrated with three reference-samples measurements and then tested over 18 experimental measurements, with good results, thereby validating the multi-parameter sensing approach.

Electric bicycle datasets for lift control have played a crucial role in the development of electric bicycle lift entry detection algorithms. However, existing datasets often encounter issues, including a small dataset size, a high false detection rate, and the absence of a publicly available benchmark dataset. This paper addresses these challenges by constructing a new electric bicycle detection dataset for lift control based on the research demands of the electric bicycle detection task for lift control. XHNet_EB, a car scene image dataset covering various types of electric bicycles, was constructed based on images taken by a camera from above. Segmented annotation was employed, framing the front and rear of the electric bicycle independently. This approach effectively addressed the problems of many irrelevant features and a high false detection rate caused by the use of whole-electric-bicycle annotations in mainstream datasets. AP_50, AP_75, the mAP, and the number of false detections in the images were used for quantitative analysis of the dataset. The experimental results indicated that the object detection accuracy of the XHNet_EB dataset was excellent. Quantitative analysis and evaluation of the number of false detections in images were conducted using four mainstream lightweight detection model algorithms. The results demonstrated that segmented annotation reduced the false detection rate more effectively than entire electric bicycle annotation. This study identified drawbacks in existing datasets. The dataset proposed in this paper overcomes the shortcomings of existing commercial data and solves problems such as the high false detection rate caused by the inclusion of many irrelevant features caused by the “whole-electric-bicycle annotation” method, which could help with the development of electric bicycle detection applications in lifts.

This paper introduces the Beethoven Piano Sonata Dataset (BPSD), a multi-version dataset focusing on the first movements of Beethoven’s 32 piano sonatas. Recognized as pivotal works in classical music, Beethoven’s piano sonatas have profoundly shaped Western classical music, holding a significant place in cultural history. The BPSD includes sheet music in different machine-readable formats and audio recordings from 11 performances, with 4 of them being in the public domain and freely accessible for research purposes. A key feature of BPSD is its coherence, ensuring alignment of all versions on a unified musical timeline and enforcing consistent structures through careful editing of both score and audio representations. The focus and main motivation for the design choices made in BPSD are on the technical and computational level. In particular, BPSD facilitates the assessment of algorithmic approaches in tasks like harmony analysis, structure analysis, music transcription, beat and downbeat estimation, and score following. The dataset’s coherence makes it an ideal platform for systematically training and evaluating deep learning methods, shedding light on their robustness and uncovering data biases across different data splits using cross-version strategies for evaluation. To ease applicability for computational approaches, the BPSD is based on various simplifications that may be disputable from a musicological perspective. Rather than providing novel musicological annotations, the main conceptual contribution of BPSD with its measure annotations is to provide a framework for transferring existing annotations from the symbolic to the audio domain. We hope that, as such, BPSD is also useful for the systematic analysis and exploration of Beethoven’s piano sonatas, providing insights into their influence on the development of harmony and structure in Western classical music. Beyond research applications, the dataset also holds educational potential, aiding in the preparation and presentation of Beethoven’s work to a broader audience through interactive multimedia experiences. This paper delivers a comprehensive overview of the BPSD, highlighting its potential for computational musicology and outlining future research directions.

This article motivates, describes, and presents the PBSCR dataset for studying composer recognition of classical piano music. Our goal was to design a dataset that facilitates large-scale research on composer recognition that is suitable for modern architectures and training practices. To achieve this goal, we utilize the abundance of sheet music images and rich metadata on IMSLP, use a previously proposed feature representation called a bootleg score to encode the location of noteheads relative to staff lines, and present the data in an extremely simple format (2-dimensional binary images) to encourage rapid exploration and iteration. The dataset itself contains 40,000 62×64 bootleg score images for a 9-class recognition task, 100,000 62×64 bootleg score images for a 100-class recognition task, and 29,310 unlabeled variable-length bootleg score images for pretraining. The labeled data is presented in a format that mirrors MNIST images in order to make it extremely easy to visualize, manipulate, and train models in an efficient manner. We include relevant information to connect each bootleg score image with its underlying raw sheet music image, and we scrape, organize, and compile metadata from IMSLP on all piano works to facilitate multimodal research and allow for convenient linking to other datasets. We release baseline results in a supervised and low-shot setting for future works to compare against, and we discuss open research questions that the PBSCR data is especially well suited to facilitate research on.

In South Korea, Asian dust frequently occurs during the spring, causing various health issues, including respiratory diseases. Consequently, public awareness and concern about air pollutants have increased, leading to demands for improved air quality and accurate forecasting. To meet these demands, the Ministry of Environment has deployed the Geostationary Environment Monitoring Spectrometer (GEMS) on the GK2B satellite to monitor atmospheric pollutants and climate change-inducing substances in real-time. The current GEMS dust product, generated using thresholds of the UV-aerosol index and visible-aerosol index, has shown limitations in accurately detecting suspended particulate matter. This study aims to develop a comprehensive AI dataset for improving GEMS Asian dust detection. Data were collected from January to May 2021, focusing on dates with significant dust events. Label data were meticulously generated through annotations based on outputs from various satellites and groundbased observations. Subsequent data preprocessing and augmentation techniques, including normalization and cut-mix, were applied to enhance the dataset’s robustness and generalizability. To evaluate the dataset, model training was conducted. The results predicted by the model showed improvements over the detection results of existing algorithms. Future datasets will be developed with improved labeling methods and accuracy verification techniques. These dataset improvements are expected to contribute to the development of deep learning models with superior predictive performance compared to current dust detection algorithms.