Open Dataset Research Articles

Analysis of white matter hyperintensities in Alzheimer’s disease and vascular dementia with magnetic resonance imaging

Objectives: The study aimed to analyze the brain white matter hyperintensities (WMHs) of patients with vascular dementia (VaD) and Alzheimer’s disease (AD) using magnetic resonance imaging to determine whether white matter lesions in the brain could be detected by a computer using image processing methods. Patients and methods: In this retrospective observational study, a unimodal, unsupervised, and automatic method was developed, and magnetic resonance imaging of 35 patients were examined. Of the 35 patients, 19 (14 males, 5 females; mean age: 73.2±6.7 years; range, 56 to 83 years) were picked from patients with AD or VaD who were admitted to a neurology clinic between January 2016 and December 2022 (Group 1). The remaining 16 patients (10 females, 5 males; mean age: 80.4±5.4 years; range, 69 to 92 years) were included from the ABVIB (Aging Brain: Vasculature, Ischemia, and Behavior) study from the ADNI (Alzheimer’s Disease Neuroimaging Initiative) database (Group 2). To calculate the volume of WMHs, a detailed analysis was conducted. Initially, skull stripping was performed, and then the brain was segmented. Afterward, two types of masks (Mask1 and Mask-2) were obtained by applying painting, decreasing, and blurring processes to the segmented white matter. These masks limited the region that was searched for WMHs. With this limitation, false positives that could arise from gray matter intensities were tried to be prevented. To evaluate the accuracy of WMH detection, a user interface was developed, and manual marking was conducted by an expert neurologist. After WMH detection, WMH volumes were calculated. Results: For Group 1, the similarity index was found to be 0.76 for Mask-1 and 0.80 for Mask-2, while for Group 2, the similarity index was 0.71 for Mask-1 and 0.87 for Mask-2. In patients with AD, the mean WMH lesion load (LL) was 15.16±16.59 mL. In patients with VaD, who were expected to suffer more from WMHs, the mean WMH LL was 29.22±11.40 mL. In Group 2, the mean WMH LL was 17.77±12.26 mL. Conclusion: This study may contribute to the literature since it is an automatic, unimodal, and unsupervised method that was applied to both a completely unique data set with many different scanning parameters and an open database data set.

Measuring Pickle Fanaticism: An open dataset for teaching instrument development and reliability

Measuring Pickle Fanaticism: An open dataset for teaching instrument development and reliability

Relative position matrix and multi-scale feature fusion for writer-independent online signature verification

Online signature verification (OSV) is widely used in finance, law and other fields, and is one of the important research projects on biological characteristics. However, its data set has a small scale and has high requirements for generalization of certification models. Therefore, how to overcome these problems is of great value to improve the practicality and security of online handwriting signature technology. We propose a writer-independent online handwritten signature verification method, which adopts the relative position matrix method to convert the traditional temporal features into images for processing. This method enriched the features of the signatures, serving the purpose of data augmentation. Then two-dimensional multi-scale feature fusion based Siamese neural network (2D-MFFnet) is built for representing and learning the importance of each channel adaptively combined with the attention mechanism. Finally, a temporal convolutional network is designed to construct the classifier. The results illustrate that compared with traditional time series models, the algorithm has reduced the equal error rate by at least 2.52 % on the open datasets MCYT-100 and SVC2004 task2.

A synthetic vulnerable population dataset for fine scale geographical equity analysis and urban planning

Assessing the social and economic vulnerability of populations within a given area is essential for conducting environmental equity evaluations and devising effective public policies to mitigate disparities. However, prevailing indicators used to measure socio-economic vulnerability exhibit several shortcomings. Primarily relying on factor analysis, these indicators face challenges in terms of comparability over time, lack of standardized scales, and inherent limitations associated with composite indicators. To address these shortcomings, we propose a novel approach that estimates the number of potentially vulnerable individuals by constructing a synthetic population. Our methodology, developed using open tools and datasets, offers a scalable solution applicable to the entire Canadian context. The resulting percentage of potentially vulnerable populations demonstrates strong correlations with traditional vulnerability indicators commonly used in Canada, while overcoming their inherent limitations. The generated dataset holds significant potential and serves as a valuable resource for both researchers and governmental organizations. It provides a robust foundation for conducting equity analyses, assessments, and policy evaluations, thereby facilitating evidence-based decision-making processes aimed at promoting social and economic inclusivity.

Estimating primary substation boundaries and the value of mapping Great Britain's electrical network infrastructure

Localised data aggregation in many countries including Great Britain (GB) is typically performed at a geographical level with polygon boundaries that have a robust and trusted governance system in place. This means there is confidence in a process to create a set of polygons that have unique identifiers coupled to geographical areas, and the ability to have these updated through a defined code of practice. Examples found across many countries are in the delivery of post, such as post codes and zip codes, and of the definition of census areas and municipal boundaries. The confidence in these boundaries allows different data to be aggregated by third parties, which itself provides greater amounts of data over comparable geographical areas to enhance wider analysis and decision making. As helpful as these polygons are for certain types of analyses, they are not specifically defined for energy systems analysis. Here we combine publicly available datasets published from the six regional electricity Distribution Network Operators of GB to produce a new geospatial dataset with 4436 unique polygons defining the areas served by electrical primary substations. An example demonstrating the value of these polygons is given to link these polygons with postcode level open government datasets on domestic energy consumption (2015–2020) from the Department of Energy Security and Net Zero (DESNZ). The resulting new data reflects energy statistics aggregated to the geographical areas served by each primary electrical substation across Great Britain. The significant value of the generated data is demonstrated by the quantification of the domestic annual heating demand presently met by natural gas across different primary substation areas which varies from an average of 5100 kWh to 28,900 kWh per property. This highlights how the rate of electrical capacity expansion will have to differ by geography under an electrified heating scenario. Therefore, we believe there is a compelling argument for all countries to set up processes to create and update polygons that have a meaningful relationship to energy systems. This would allow more accurate energy systems analysis to be performed, ultimately leading to an accelerated or potentially lower cost transition to a net zero world.

Towards SDG 11: Large-scale geographic and demographic characterisation of informal settlements fusing remote sensing, POI, and open geo-data

Informal settlements’ geographic and demographic mapping is essential for evaluating human-centric sustainable development in cities, thus fostering the road to Sustainable Development Goal 11. However, fine-grained informal settlements’ geographic and demographic information is not well available. To fill the gap, this study proposes an effective framework for both fine-grained geographic and demographic characterisation of informal settlements by integrating openly available remote sensing imagery, points-of-interest (POI), and demographic data. Pixel-level informal settlement is firstly mapped by a hierarchical recognition method with satellite imagery and POI. The patch-scale and city-scale geographic patterns of informal settlements are further analysed with landscape metrics. Spatial-demographic profiles are depicted by linking with the open WorldPop dataset to reveal the demographic pattern. Taking the Guangdong-Hong Kong-Macao Greater Bay Area (GBA) in China as the study area, the experiment demonstrates the effectiveness of informal settlement mapping, with an overall accuracy of 91.82%. The aggregated data and code are released (https://github.com/DongshengChen9/IF4SDG11). The demographic patterns of the informal settlements reveal that Guangzhou and Shenzhen, the two core cities in the GBA, concentrate more on young people living in the informal settlements. While the rapid-developing city Shenzhen shows a more significant trend of gender imbalance in the informal settlements. These findings provide valuable insights into monitoring informal settlements in the urban agglomeration and human-centric urban sustainable development, as well as SDG 11.1.1.

A Comparative Performance Evaluation of YOLO-Type Detectors on a New Open Fire and Smoke Dataset.

The paper introduces a new FireAndSmoke open dataset comprising over 22,000 images and 93,000 distinct instances compiled from 1200 YouTube videos and public Internet resources. The scenes include separate and combined fire and smoke scenarios and a curated set of difficult cases representing real-life circumstances when specific image patches may be erroneously detected as fire/smoke presence. The dataset has been constructed using both static pictures and video sequences, covering day/night, indoor/outdoor, urban/industrial/forest, low/high resolution, and single/multiple instance cases. A rigorous selection, preprocessing, and labeling procedure has been applied, adhering to the findability, accessibility, interoperability, and reusability specifications described in the literature. The performances of the YOLO-type family of object detectors have been compared in terms of class-wise Precision, Recall, Mean Average Precision (mAP), and speed. Experimental results indicate the recently introduced YOLO10 model as the top performer, with 89% accuracy and a mAP@50 larger than 91%.

Enhanced 3D object detection for autonomous driving: A spatial-temporal alignment approach in Bird's Eye View scenarios

This paper presents a novel 3D object detection algorithm designed for Bird's Eye View (BEV) scenarios, which significantly improves detection capabilities by integrating spatial and temporal features. The core of our approach is the spatial-temporal alignment module that efficiently processes information across different time steps and spatial locations, enhancing the precision and robustness of object detection. We employ a temporal self-attention mechanism to capture the motion information of objects over time, allowing the model to correlate features across various time steps for identifying and tracking moving objects. Additionally, a spatial cross-attention mechanism is utilized to focus on spatial features within regions of interest, promoting interactions between features extracted from camera views and BEV queries. Our method also implements temporal feature integration and multi-scale feature fusion to enhance detection stability and accuracy for fast-moving objects and to capture multi-scale context information, respectively. The model employs an enriched feature set post alignment for 3D bounding box prediction, ascertaining the position, dimensions, and orientation of objects. We conducted experiments on two public datasets for autonomous driving nuScenes and Waymo Open Dataset, demonstrating that our method outperforms previous BEVFormer and other state-of-the-art methods in terms of detection accuracy and robustness. The paper concludes with potential future directions for optimizing the BEVFormer model's performance and exploring its application in broader scenarios and tasks.

Machine Learning for public transportation demand prediction: A Systematic Literature Review

Within the Intelligent Public Transportation Systems (IPTS) field, the prediction of public transportation demand is a key point for enhancing the quality of the services. These predictions can be exploited by transit operators, for service planning and management, as well as by passengers, for planning their trips. Hence, the public transportation demand prediction problem is being more and more investigated by the scientific community, with several different proposals in terms of Machine Learning (ML) techniques, employed sensors, considered external features, and so on. However, there is a lack of comprehensive reviews that summarize and organize the available proposals on this topic. Hence, researchers intending to propose novel ML solutions, and practitioners willing to implement such solutions, may be overwhelmed by the plethora and heterogeneity of scientific work.To support these kinds of profiles, in this paper, we provide a Systematic Literature Review on ML techniques for predicting public transportation demand. This review highlights a growing interest by the scientific community on this topic, but also the lack of open datasets (useful for benchmarking), and in general of reproducible studies. Moreover, while deep learning techniques are frequently favored for their potential in terms of accuracy, associated costs, interpretability, and energy consumption are often overlooked.

A dataset of optical camera and IMU sensor derived kinematics of thirty transtibial prosthesis wearers

Motion analysis has played a crucial role in providing gait analysis for prosthetic users. Understanding kinematics in motion analysis allows for the evaluation of the effects of prostheses and the development of a prosthetic component design that aids in walking within the community. However, there are currently limited open datasets available to study the locomotion of individuals using transtibial prostheses, and most research studies involve a limited number of participants. This dataset shows 30 transtibial prosthesis users walking comfortably on a 10-meter walkway inside a laboratory. We offer a set of joint ankles obtained from the inertial measurement unit (IMU) signals in CSV file format. We also provide the optical motion capture (OMC) system’s raw trajectory marker data in C3D file format and joint angle in CSV file format. This open dataset will provide resources for professionals interested in amputee gait for research in amputee gait detection and tracking algorithms. Moreover, the data will be the control data for comparison in developing advanced prosthetic components.

A Reproducible Stress Prediction Pipeline with Mobile Sensor Data

Recent efforts to predict stress in the wild using mobile technology have increased; however, the field lacks a common pipeline for assessing the impact of factors such as label encoding and feature selection on prediction performance. This gap hinders replication, especially because of a lack of common guidelines for reporting results or privacy concerns that limit access to open codes and datasets. Our study introduces a common pipeline based on a comprehensive literature review and offers comprehensive evaluations of key pipeline factors, promoting independent reproducibility. Our systematic evaluation aimed to validate the findings of previous studies. We identified overfitting and distribution shifts across users as the major reasons for performance limitations. We used K-EmoPhone, a public dataset, for experimentation and a new public dataset---DeepStress---to validate the findings. Furthermore, our results suggest that researchers should carefully consider temporal order in cross-validation settings. Additionally, self-report labels for target users are key to enhancing performance in user-independent scenarios.

Roof plane parsing towards LoD-2.2 building reconstruction based on joint learning using remote sensing images

Building models are important for urban studies. Remote sensing multi-spectral (MS) images are widely used for its rich semantic information. The lack of geometry features is fulfilled by introducing photogrammetry derived digital surface models (DSMs), resulting in pairs of DSMs and MS images. Utilizing such pairs and a convolutional neural network, level of detail (LoD) 2.2 building models, which contain roof planes and major roof elements (e.g. dormers), are reconstructed in this work. Leveraging both raster and vector predictions, 3-D building models with straight edges and sharp corners are obtained. The proposed two-stage method first extracts vectorized roof lines from pairs of DSMs and RGB images, followed by generation of detailed 2-D and 3-D polygonal building models. We conducted our experiments based on two datasets: a custom dataset in Landsberg am Lech in Germany, and an open dataset named Roof3D. For the custom dataset, our proposed model achieved mean average precision (mAP) for building roof vertices of 64.3% and for building roof lines of 54.5% at highest. Mean precision and recall for reconstructed 2-D building roof plane polygons are 52.2% and 54.7% respectively. For the Roof3D dataset, mAP is reported to be 25.3% and 12.4% for the extracted building roof lines and roof plane polygons respectively.

BVTED: A Specialized Bilingual (Chinese–English) Dataset for Vulnerability Triple Extraction Tasks

Extracting knowledge from cyber threat intelligence is essential for understanding cyber threats and implementing proactive defense measures. However, there is a lack of open datasets in the Chinese cybersecurity field that support both entity and relation extraction tasks. This paper addresses this gap by analyzing vulnerability description texts, which are standardized and knowledge-dense, to create a vulnerability knowledge ontology comprising 13 entities and 15 relations. We annotated 27,311 unique vulnerability description sentences from the China National Vulnerability Database, resulting in a dataset named BVTED for cybersecurity knowledge triple extraction tasks. BVTED contains 97,391 entities and 69,614 relations, with entities expressed in a mix of Chinese and English. To evaluate the dataset’s value, we trained five deep learning-based named entity recognition models, two relation extraction models, and two joint entity–relation extraction models on BVTED. Experimental results demonstrate that models trained on this dataset achieve excellent performance in vulnerability knowledge extraction tasks. This work enhances the extraction of cybersecurity knowledge triples from mixed Chinese and English threat intelligence corpora by providing a comprehensive ontology and a new dataset, significantly aiding in the mining, analysis and utilization of the knowledge embedded in cyber threat intelligence.

Near Pan-Svalbard permafrost cryospheric hazards inventory (SvalCryo)

Cryospheric hazards - in this case, thaw slumps (TS) and thermo-erosion gullies (TEG) - are phenomena typical of permafrost-dominated landscapes. Open datasets informing about their spatial, temporal and size distributions in the Arctic are still uncommon, as opposed to the systematic availability of this information for geomorphic processes in mid- to low- latitudes. To date, only the most populated region of Svalbard was covered with TS and TEG inventories. Here, we extend the respective information to most of the Archipelago, totalling 8491 polygons, out of which 3679 are TSs and 4812 are TEGs. These have been manually mapped from aerial photographs throughout Svalbard across the 14 largest ice-free regions. The SvalCryo inventory is highly relevant as the Arctic environment undergoes alarming changes in response to global warming. The idea behind the two inventories is to support the geoscientific community in the quest to evaluate the environmental response to climate change, by creating a baseline for change monitoring, and ultimately to serve as basis for susceptibility, hazard and risk assessment models.

An interval-valued matrix factorization based trust-aware collaborative filtering algorithm for recommendation systems

In existing trust-aware collaborative filtering algorithms, each trust relationship between two users is usually represented by a real number, but such a number is neither sufficient to reflect the quantity of the trust relationship existing in the user’s mind nor easy to be given. This leads to the inaccuracy of the trust relationship and poor final recommendations. To solve this problem, we propose an approach to deduce interval-valued trust relationships from the given real-valued trust relationships, which enables the new trust relationships to optimally reflect the true trust relationships existing in users’ minds. The coming problem we face is how to fuse the interval-valued trust relationships and the real-valued ratings. Though most existing trust-aware collaborative filtering algorithms use matrix factorization to fuse the real-valued data, they are not capable of fusing interval-valued trust relationships and real-valued ratings. The reason is that the arithmetic operations on intervals and arithmetic operations on real numbers are different. Therefore, we proposed a novel interval-valued matrix factorization approach. After that, an interval-valued matrix factorization based trust-aware collaborative filtering (IMF_TCF) algorithm is designed. The experiments carried out with open datasets indicate that IMF_TCF achieves the best recommendation performance compared with the state-of-the-art algorithms.

A comprehensive review of retinal disease diagnosis and open access datasets: Fundus and OCT images

The rapid advancements in deep learning algorithms and the availability of large, open-access databases of fundus and OCT (optical coherence tomography) images have contributed greatly to advancements in computer-assisted diagnostics and the localization of various disorders affecting the retina. This study offers a comprehensive examination of retinal diseases and various recent applications of deep learning strategies for categorising key retinal conditions, such as diabetic retinopathy, glaucoma, age-related macular degeneration, choroidal neovascularization, retinal detachment, media haze, myopia, and dry eyes. Open-access datasets continue to play a critical role in the advancement of digital health research and innovation within the field of ophthalmology. Thirty open-access databases containing fundus and OCT (optical coherence tomography) pictures, which are often utilised by researchers, were carefully examined in this work. A summary of these datasets was created, which includes the number of images, dataset size, and supplementary items in the dataset, as well as information on eye disease and country of origin. We also discussed challenges and limitations of novel deep learning models. Finally, in conclusion, we discussed some important insights and provided directions for future research opportunities.

Application of deep learning-based Intrusion Detection System (IDS) in network anomaly traffic detection

This study discusses the application of deep learning technology in network intrusion detection systems (IDS) and focuses on a new model named CNN-Focal. First, reviewing traditional IDS technology, it analyzes its limitations in dealing with complex network traffic. Then, the design principle of the CNN-Focal model is described in detail, which uses threshold convolution and SoftMax multi-class classification technology to improve abnormal traffic detections accuracy and efficiency effectively. The experimental results show that CNN-Focal performs well on the open data set, demonstrating the potential and advantages of its application in the natural network environment and providing a new perspective and method for further research of deep learning in the field of network security in the future.

A robust operators’ cognitive workload recognition method based on denoising masked autoencoder

Identifying the cognitive workload of operators is crucial in complex human-automation collaboration systems. An excessive workload can lead to fatigue or accidents, while an insufficient workload may diminish situational awareness and efficiency. However, existing supervised learning-based methods for workload recognition are ineffective when dealing with imperfect input data, such as missing or noisy data, which is not practical in real applications. This study introduces a robust Electroencephalogram (EEG)-enabled cognitive workload recognition model using self-supervised learning. The proposed method, DMAEEG, combines the training strategies of denoising autoencoders and masked autoencoders, demonstrating strong robustness against noisy and incomplete data. More specifically, we adopt the temporal convolutional network and multi-head self-attention mechanisms as the backbone, effectively capturing both the temporal and spatial features from EEG. Extensive experiments are conducted to verify the effectiveness and robustness of the proposed method on an open dataset and a self-collected dataset. The results indicate that DMAEEG performs superior to other state-of-the-art across various evaluation metrics. Moreover, DMAEEG maintains high accuracy in workload inference even when EEG signals are corrupted with a high masking ratio or strong noises. This signifies its superiority in capturing robust intrinsic patterns from imperfect EEG data. The proposed method significantly contributes to decoding EEG signals for workload recognition in real-world applications, thereby enhancing the safety and reliability of human-automation interactions.

SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data

This study focuses on advancing individual tree crown (ITC) segmentation in lidar data, developing a sensor- and platform-agnostic deep learning model transferable across a spectrum of dense laser scanning datasets from drone (ULS), to terrestrial (TLS), and mobile (MLS) laser scanning data. In a field where transferability across different data characteristics has been a longstanding challenge, this research marks a step towards versatile, efficient, and comprehensive 3D forest scene analysis.Central to this study is model performance evaluation based on platform type (ULS vs. MLS) and data density. This involved five distinct scenarios, each integrating different combinations of input training data, including ULS, MLS, and their augmented versions through random subsampling, to assess the model's transferability to varying resolutions and efficacy across different canopy layers. The core of the model, inspired by the PointGroup architecture, is a 3D convolutional neural network (CNN) with dedicated prediction heads for semantic and instance segmentation. The model underwent comprehensive validation on publicly available, machine learning-ready point cloud datasets. Additional analyses assessed model adaptability to different resolutions and performance across canopy layers.Our results reveal that point cloud random subsampling is an effective augmentation strategy and improves model performance and transferability. The model trained using the most aggressive augmentation, including point clouds as sparse as 10 points m−2, showed best performance and was found to be transferable to sparse lidar data and boosts detection and segmentation of codominant and dominated trees. Notably, the model showed consistent performance for point clouds with densities >50 points m−2 but exhibited a drop in performance at the sparsest level (10 points m−2), mainly due to increased omission rates. Benchmarking against current state-of-the-art methods revealed boosts of up to 20% in the detection rates, indicating the model's superior performance on multiple open benchmark datasets. Further, our experiments also set new performance baselines for the other public datasets. The comparison highlights the model's superior segmentation skill, mainly due to better detection and segmentation of understory trees below the canopy, with reduced computational demands compared to other recent methods.In conclusion, the present study demonstrates that it is indeed feasible to train a sensor-agnostic model that can handle diverse laser scanning data, going beyond current sensor-specific methodologies. Further, our study sets a new baseline for tree segmentation, especially in complex forest structures. By advancing the state-of-the-art in forest lidar analysis, our work also lays the foundation for future innovations in ecological modeling and forest management.

Subject-independent auditory spatial attention detection based on brain topology modeling and feature distribution alignment

Auditory spatial attention detection (ASAD) seeks to determine which speaker in a surround sound field a listener is focusing on based on the one’s brain biosignals. Although existing studies have achieved ASAD from a single-trial electroencephalogram (EEG), the huge inter-subject variability makes them generally perform poorly in cross-subject scenarios. Besides, most ASAD methods do not take full advantage of topological relationships between EEG channels, which are crucial for high-quality ASAD. Recently, some advanced studies have introduced graph-based brain topology modeling into ASAD, but how to calculate edge weights in a graph to better capture actual brain connectivity is worthy of further investigation. To address these issues, we propose a new ASAD method in this paper. First, we model a multi-channel EEG segment as a graph, where differential entropy serves as the node feature, and a static adjacency matrix is generated based on inter-channel mutual information to quantify brain functional connectivity. Then, different subjects’ EEG graphs are encoded into a shared embedding space through a total variation graph neural network. Meanwhile, feature distribution alignment based on multi-kernel maximum mean discrepancy is adopted to learn subject-invariant patterns. Note that we align EEG embeddings of different subjects to reference distributions rather than align them to each other for the purpose of privacy preservation. A series of experiments on open datasets demonstrate that the proposed model outperforms state-of-the-art ASAD models in cross-subject scenarios with relatively low computational complexity, and feature distribution alignment improves the generalizability of the proposed model to a new subject.