Search

With the rapid advancement of urban intelligence, there is an increasingly urgent demand for technological innovation in traffic management. License plate recognition technology can achieve high accuracy under ideal conditions but faces significant challenges in complex traffic environments and adverse weather conditions. To address these challenges, we propose the enhanced attention network and decoding for license plate recognition model (EAND-LPRM). This model leverages an encoder to extract features from image sequences and employs a self-attention mechanism to focus on critical feature information, enhancing its capability to handle complex traffic scenarios such as rainy weather and license plate distortion. We have curated and utilized publicly available datasets that closely reflect real-world scenarios, ensuring transparency and reproducibility. Experimental evaluations conducted on these datasets, which include various complex scenarios, demonstrate that the EAND-LPRM model achieves an accuracy of 94%, representing a 6% improvement over traditional license plate recognition algorithms. The main contributions of this research include the development of a novel attention-mechanism-based architecture, comprehensive evaluation on multiple datasets, and substantial performance improvements under diverse and challenging conditions. This study provides a practical solution for automatic license plate recognition systems in dynamic and unpredictable environments. [ABSTRACT FROM AUTHOR]

Automated text summarization (ATS) systems rely on language resources as datasets. However, creating these datasets is a complex and labor-intensive task requiring linguists to extensively annotate the data. Consequently, certain public datasets for ATS, particularly in languages such as Thai, are not as readily available as those for the more popular languages. The primary objective of the ATS approach is to condense large volumes of text into shorter summaries, thereby reducing the time required to extract information from extensive textual data. Owing to the challenges involved in preparing language resources, publicly accessible datasets for Thai ATS are relatively scarce compared to those for widely used languages. The goal is to produce concise summaries and accelerate the information extraction process using vast amounts of textual input. This study introduced ThEconSum, an ATS architecture specifically designed for Thai language, using economy-related data. An evaluation of this research revealed the significant remaining tasks and limitations of the Thai language. [ABSTRACT FROM AUTHOR]

The automated inspection of weld beads is of great importance for many industrial processes. Failures may cause a loss of mechanical resistance of the weld bead and compromise the manufactured part. Several methods have been proposed in the literature to address this problem, and recently, methods based on deep learning have gained prominence in terms of performance and applicability. However, such methods require vast and reliable datasets for different real defects, which have yet to be available in recent literature. Hence, this paper presents LoHi-WELD, an original and public database to address the problem of weld defect detection and classification of four common types of defects — pores, deposits, discontinuities, and stains — with 3,022 real weld bead images manually annotated for visual inspection, composed by low and high-resolution images, acquired from a Metal Active Gas robotic welding industrial process. We also explore variations of a baseline deep architecture for the proposed dataset based on a YOLOv7 network and discuss several case analyses. We show that a lightweight architecture, ideal for industrial edge devices, can achieve up to 0.69 of mean average precision (mAP) considering a fine-grained defect classification and 0.77 mAP for a coarse classification. Open challenges are also presented, promoting future research and enabling robust solutions for industrial scenarios. The proposed dataset, architecture, and trained models are publicly available on https://github.com/SylvioBlock/LoHi-Weld.

Wi-Fi based human activity recognition is emerging and preferable over other approaches due to its numerous advantages, including privacy considerations, ubiquitousness, and easy deployment. While existing literature predominantly focuses on identifying the activities of a single-user, recognizing multi-person interactions (MPIs) is increasingly significant due to their profound social implications. However, research in this area has not progressed due to the limitation of publicly available Wi-Fi datasets and the complexities of MPI recognition. Motivated by this, we develop and publicly release a Wi-Fi channel state information (CSI) based MPI recognition dataset, coined Wi-MIR, that uses three transmit and three receive antennas to capture 270 ( $ {3}\times {3}\times {30}$ ) subcarriers with a sampling rate of 950 Hz. This dataset consists of 3740 trials encompassing seventeen distinct MPIs and is collected by eleven human pairs in an indoor environment. We put forth a lightweight deep learning model with attention mechanisms for MPI recognition from CSI, named CSI-IRNet, that adeptly concentrates on pertinent features, filtering out irrelevant elements, and mitigating the impact of signal complexity within the CSI for recognizing MPIs accurately. In addition, we compare the developed Wi-MIR and the existing public dataset by evaluating the performance of MPI recognition on both datasets to highlight the strengths and advancements provided by Wi-MIR. The evaluation results show that Wi-MIR dataset demonstrates a superior recognition performance by utilizing more subcarriers with a higher sampling rate as well as covering more diverse kinds of MPIs (Bowing, Conversation, Exchanging objects, Helping standup, Helping walk, and Touching another person).

Modern manufacturing industry relies on complex machinery that requires skills, attention, and precise safety certifications. Protecting operators in the machine’s surroundings while at the same time reducing the impact on the normal workflow is a major challenge. In particular, safety systems based on proximity sensing of humans or obstacles require that the detection is accurate, low-latency, and robust against variations in environmental conditions. This work proposes a functional safety solution for collision avoidance relying on Ultrasounds (US) and a Temporal Convolutional Network (TCN) suitable for deployment directly at the edge on a low-power Microcontroller Unit (MCU). The setup allowed to acquire a sensor-fusion dataset with 9 US sensors mounted on a real industrial woodworking machine. Applying incremental training, the proposed TCN achieved sensitivity 90.5%, specificity 95.2%, and AUROC 0.972 on data affected by the typical acoustic noise of an industrial facility, an accuracy comparable with the State-of-the-Art (SoA). Deployment on an STM32H7 MCU yielded a memory footprint of 560 B (3× less than SoA), with an extremely low latency of 5.0 ms and an energy consumption of 8.2 mJ per inference (both >2.3× less than SoA). The proposed solution increases its robustness against acoustic noise by leveraging new data, and it fits the resource budget of real-time operation execution on resource-constrained embedded devices. It is thus promising for generalization to different industrial settings and for scale-up to wider monitored spaces.

Accurate and fast classification of FDEs is crucial to power systems situation awareness and stability control. However, various database used in recent studies makes it hard to directly compare different classification methods. To relieve the lack of a standardized database that can be used as a benchmark, this work proposes an open-source package which generates frequency events based on PowerFactory named PF-FEDG. PF-FEDG can produce various labeled FDEs with random parameters such as generator trips, load disconnections, line outages, frequency ramp ups, frequency ramp downs, and frequency oscillations. Furthermore, the package includes three reference FDEs classifiers based on deep learning techniques. These models are tested on the IEEE 39-bus system and IEEE 118-bus system and achieve high performance. The package generating capability and the reference classifiers can be used by the community as benchmarks for comparison and development of new algorithms for FDEs detection. The code of PF-FEDG is available on GitLab.

This paper is focused on the field of computer vision in order to investigate the presentation properties of retinal blood vessels. Combining the structure of convolutional neural networks, activation functions, and common metrics in semantic segmentation, a dynamic network model for retinal vessel segmentation based on computer vision is constructed. The purpose of this paper is to discuss the results of retinal vascular segmentation based on computer vision. The image connection and alignment pattern selection process is also established to match retinal vessel images by computer vision. The performance of the dynamic network constructed here and the results of retinal vessel segmentation were then analyzed in three publicly available datasets, DRIVE (digital retinal images for vessel extraction), CHASE_DB1, and STARE (structured snalysis of the retinal. The ROC (retinopathy online challenge) curves on all three datasets exceeded 0.9, showing high performance, and the area under the PR curve exceeded 0.88. The accuracy of the results for retinal vessel segmentation was around 96%. Based on the semantic segmentation direction in the field of computer vision in this study, the dynamic network for retinal vessel segmentation can be well constructed. [ABSTRACT FROM AUTHOR]

With the rapid advancement of urban intelligence, there is an increasingly urgent demand for technological innovation in traffic management. License plate recognition technology can achieve high accuracy under ideal conditions but faces significant challenges in complex traffic environments and adverse weather conditions. To address these challenges, we propose the enhanced attention network and decoding for license plate recognition model (EAND-LPRM). This model leverages an encoder to extract features from image sequences and employs a self-attention mechanism to focus on critical feature information, enhancing its capability to handle complex traffic scenarios such as rainy weather and license plate distortion. We have curated and utilized publicly available datasets that closely reflect real-world scenarios, ensuring transparency and reproducibility. Experimental evaluations conducted on these datasets, which include various complex scenarios, demonstrate that the EAND-LPRM model achieves an accuracy of 94%, representing a 6% improvement over traditional license plate recognition algorithms. The main contributions of this research include the development of a novel attention-mechanism-based architecture, comprehensive evaluation on multiple datasets, and substantial performance improvements under diverse and challenging conditions. This study provides a practical solution for automatic license plate recognition systems in dynamic and unpredictable environments.

This study proposes a Synthetic Aperture Radar (SAR) aircraft detection and recognition method combined with scattering perception to address the problem of target discreteness and false alarms caused by strong background interference in SAR images. The global information is enhanced through a context-guided feature pyramid module, which suppresses strong disturbances in complex images and improves the accuracy of detection and recognition. Additionally, scatter key points are used to locate targets, and a scatter-aware detection module is designed to realize the fine correction of the regression boxes to improve target localization accuracy. This study generates and presents a high-resolution SAR-AIRcraft-1.0 dataset to verify the effectiveness of the proposed method and promote the research on SAR aircraft detection and recognition. The images in this dataset are obtained from the satellite Gaofen-3, which contains 4,368 images and 16,463 aircraft instances, covering seven aircraft categories, namely A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and other. We apply the proposed method and common deep learning algorithms to the constructed dataset. The experimental results demonstrate the excellent effectiveness of our method combined with scattering perception. Furthermore, we establish benchmarks for the performance indicators of the dataset in different tasks such as SAR aircraft detection, recognition, and integrated detection and recognition.

As a biometric technology, gait recognition is usually considered a retrieval task in real life. However, because of the small scale of the existing radar gait recognition dataset, the current studies mainly focus on classification tasks and only consider the situation of a single walking view and the same wearing condition, limiting the practical application of radar-based gait recognition. This paper provides a radar gait recognition dataset under multi-view and multi-wearing conditions; the dataset uses millimeter-wave radar as a sensor to collect the time-frequency spectrogram data of 121 subjects walking along views under multiple wearing conditions. Eight views were collected for each subject, and ten sets were collected for each view. Six of the ten sets are dressed normally, two are dressed in coats, and the last two are carrying bags. Meanwhile, this paper proposes a method for radar gait recognition based on retrieval tasks. Experiments are conducted on this dataset, and the experimental results can be used as a benchmark to facilitate further research by related scholars on this dataset.

Fall accidents in industrial and construction environments require an immediate reaction, to provide first aid. Shortening the time between the fall and the relevant personnel being notified can significantly improve the safety and health of workers. Therefore, in this work, an IoT system for real-time fall detection is proposed, using the ASSIST-IoT reference architecture. Empowered with a machine learning model, the system can detect fall accidents and swiftly notify the occupational health and safety manager. To train the model, a novel multimodal fall detection dataset was collected from ten human participants and an anthropomorphic dummy, covering multiple types of fall, including falls from a height. The dataset includes absolute location and acceleration measurements from several IoT devices. Furthermore, a lightweight long short-term memory model is proposed for fall detection, capable of operating in an IoT environment with limited network bandwidth and hardware resources. The accuracy and F1-score of the model on the collected dataset were shown to exceed 0.95 and 0.9, respectively. The collected multimodal dataset was published under an open license, to facilitate future research on fall detection methods in occupational health and safety. [ABSTRACT FROM AUTHOR]

This work analyzes a new indoor laboratory dataset looking at early fire indicators in controlled and realistic experiments representing different incipient fire scenarios. The experiments were performed within the constraints of an indoor laboratory setting using multiple distributed sensor nodes in different room positions. Each sensor node collected data of particulate matter (PM), volatile organic compounds (VOCs), carbon monoxide (CO), carbon dioxide (CO 2 ), hydrogen (H 2 ), ultraviolet radiation (UV), air temperature, and humidity in terms of a multivariate time series. These data hold immense value for researchers within the machine learning and data science communities who are keen to explore innovative and advanced statistical and machine learning techniques. They serve as a valuable resource for the development of early fire detection systems. The analysis of the collected data was carried out depending on the Manhattan distance between the fire source and the sensor node. We found that especially larger particles (>0.5 μ m) and VOCs show a significant dependency with respect to the intensity as a function of the Manhattan distance to the source. Moreover, we observed differences in the propagation behavior of VOCs, PM, and CO, which are particularly relevant in incipient fire scenarios due to the presence of strand propagation effects. [ABSTRACT FROM AUTHOR]

The demand for public datasets has increased as data-driven methodologies have been introduced in the field of brain-computer interfaces (BCIs). Indeed, many BCI datasets are available in various platforms or repositories on the web, and the studies that have employed these datasets appear to be increasing. Motor imagery is one of the significant control paradigms in the BCI field, and many datasets related to motor tasks are open to the public already. However, to the best of our knowledge, these studies have yet to investigate and evaluate the datasets, although data quality is essential for reliable results and the design of subject- or system-independent BCIs. In this study, we conducted a thorough investigation of motor imagery/execution EEG datasets recorded from healthy participants published over the past 13 years. The 25 datasets were collected from six repositories and subjected to a meta-analysis. In particular, we reviewed the specifications of the recording settings and experimental design, and evaluated the data quality measured by classification accuracy from standard algorithms such as Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) for comparison and compatibility across the datasets. As a result, we found that various stimulation types, such as text, figure, or arrow, were used to instruct subjects what to imagine and the length of each trial also differed, ranging from 2.5 to 29 s with a mean of 9.8 s. Typically, each trial consisted of multiple sections: pre-rest (2.38 s), imagination ready (1.64 s), imagination (4.26 s, ranging from 1 to 10 s), the post-rest (3.38 s). In a meta-analysis of the total of 861 sessions from all datasets, the mean classification accuracy of the two-class (left-hand vs. right-hand motor imagery) problem was 66.53%, and the population of the BCI poor performers, those who are unable to reach proficiency in using a BCI system, was 36.27% according to the estimated accuracy distribution. Further, we analyzed the CSP features and found that each dataset forms a cluster, and some datasets overlap in the feature space, indicating a greater similarity among them. Finally, we checked the minimal essential information (continuous signals, event type/latency, and channel information) that should be included in the datasets for convenient use, and found that only 71% of the datasets met those criteria. Our attempts to evaluate and compare the public datasets are timely, and these results will contribute to understanding the dataset's quality and recording settings as well as the use of using public datasets for future work on BCIs. [ABSTRACT FROM AUTHOR]

The thalamus is a subcortical brain structure linked to the motor system. Since certain changes within this structure are related to diseases, such as multiple sclerosis and Parkinson's, the characterization of the thalamus—e.g., shape assessment—is a crucial step in relevant studies and applications, including medical research and surgical planning. A robust and reliable thalamus-segmentation method is therefore, required to meet these demands. Despite presenting low contrast for this particular structure, T1-weighted imaging is still the most common MRI sequence for thalamus segmentation. However, diffusion MRI (dMRI) captures different micro-structural details of the biological tissue and reveals more contrast of the thalamic borders, thereby serving as a better candidate for thalamus-segmentation methods. Accordingly, we propose a baseline multimodality thalamus-segmentation pipeline that combines dMRI and T1-weighted images within a CNN approach, achieving state-of-the-art levels of Dice overlap. Furthermore, we are hosting an open benchmark with a large, preprocessed, publicly available dataset that includes co-registered, T1-weighted, dMRI, manual thalamic masks; masks generated by three distinct automated methods; and a STAPLE consensus of the masks. The dataset, code, environment, and instructions for the benchmark leaderboard can be found on our GitHub and CodaLab. [ABSTRACT FROM AUTHOR]

This paper releases a rotated SAR ship detection dataset, named Rotated Ship Detection Dataset in SAR Images (RSDD-SAR), to address the problem that the existing rotated SAR ship detection datasets are not enough to meet the requirements of algorithm development and practical application. This dataset consists of 84 scenes of GF-3 data slices, 41 scenes of TerraSAR-X data slices, and 2 scenes of large uncropped images, including 7,000 slices and 10,263 ship instances of multi-observing modes, multi-polarization modes, and multi-resolutions. This dataset is effectively annotated by automatic annotation with manual correction. Meanwhile, experiments were conducted for several popular rotated object detection algorithms in optical remote sensing images and rotated ship detection algorithms in SAR images, and the one-stage algorithm S2ANet achieved the highest average precision of 90.06%. When using this dataset, scholars can reference the experimental results, and corresponding analysis can be used. Finally, this paper conducts generalization ability testing experiments on other datasets and large uncropped images to analyze and discuss the performance of the model trained on RSDD-SAR. The experimental results show that the model trained on RSDD-SAR has decent performance and confirms the application value of this dataset. The RSDD-SAR dataset is available at https://radars.ac.cn/web/data/getData?dataType=SDD-SAR.

The fields of developmental psychopathology, developmental neuroscience, and behavioral genetics are increasingly moving toward a data sharing model to improve reproducibility, robustness, and generalizability of findings. This approach is particularly critical for understanding attention-deficit/hyperactivity disorder (ADHD), which has unique public health importance given its early onset, high prevalence, individual variability, and causal association with co-occurring and later developing problems. A further priority concerns multi-disciplinary/multi-method datasets that can span different units of analysis. Here, we describe a public dataset using a case-control design for ADHD that includes: multi-method, multi-measure, multi-informant, multi-trait data, and multi-clinician evaluation and phenotyping. It spans > 12 years of annual follow-up with a lag longitudinal design allowing age-based analyses spanning age 7–19 + years with a full age range from 7 to 21. Measures span genetic and epigenetic (DNA methylation) array data; EEG, functional and structural MRI neuroimaging; and psychophysiological, psychosocial, clinical and functional outcomes data. The resource also benefits from an autism spectrum disorder add-on cohort and a cross sectional case-control ADHD cohort from a different geographical region for replication and generalizability. Datasets allowing for integration from genes to nervous system to behavior represent the “next generation” of researchable cohorts for ADHD and developmental psychopathology.

Purpose: This study aimed at developing a deep learning-based method for multi-label thoracic abnormality classification on frontal view chest X-ray (CXR). To improve the performance of classification, issues of class imbalance, noisy labels and ensemble of networks are addressed in the paper. Methods: The experiments were performed on a public dataset called Chest X-ray 14 (CXR14), which includes 112,120 frontal view CXRs from 30,805 patients. We came up with an ensemble learning framework to improve the classification and a noisy label detection method to detect the CXRs with noisy labels. The detected CXRs were reviewed by two board-certificated radiologists in a consensus fashion to evaluate detected noisy labels. The classification was assessed on CXR14 with area under the receiver operating characteristic curve (AUC). Results: Report from the radiologists indicated that detected noisy labels had high possibility to be true positives. A notable improvement from baseline in performance of classification was observed with the ensemble learning framework. After removing the CXRs with detected noisy labels, 8 out of 14 abnormalities improved significantly on CXR14. The suggested framework achieved AUC score of 0.827 on CXR14. Conclusion: The methods of this study boost the classification on CXR with awareness of the label noise. Expanded experimental results show that all of them were able to improve multi-label thoracic abnormality classification performance, respectively. A new state-of-the-art is achieved in this study. [ABSTRACT FROM AUTHOR]

Measuring and adjusting the training load is essential in resistance training, as training overload can increase the risk of injuries. At the same time, too little load does not deliver the desired training effects. Usually, external load is quantified using objective measurements, such as lifted weight distributed across sets and repetitions per exercise. Internal training load is usually assessed using questionnaires or ratings of perceived exertion (RPE). A standard RPE scale is the Borg scale, which ranges from 6 (no exertion) to 20 (the highest exertion ever experienced). Researchers have investigated predicting RPE for different sports using sensor modalities and machine learning methods, such as Support Vector Regression or Random Forests. This paper presents PERSIST, a novel dataset for predicting PERceived exertion during reSIStance Training. We recorded multiple sensor modalities simultaneously, including inertial measurement units (IMU), electrocardiography (ECG), and motion capture (MoCap). The MoCap data has been synchronized to the IMU and ECG data. We also provide heart rate variability (HRV) parameters obtained from the ECG signal. Our dataset contains data from twelve young and healthy male participants with at least one year of resistance training experience. Subjects performed twelve sets of squats on a Flywheel platform with twelve repetitions per set. After each set, subjects reported their current RPE. We chose the squat exercise as it involves the largest muscle group. This paper demonstrates how to access the dataset. We further present an exploratory data analysis and show how researchers can use IMU and ECG data to predict perceived exertion. [ABSTRACT FROM AUTHOR]

This forum article provides an overview of the sampling and survey design of the publicly available InterCov dataset. The two-wave cross-country survey includes items on lobbying mobilisation, strategies, access and influence after the outbreak of the COVID-19 pandemic, and other measures of organisational factors. We discuss design choices considering our interest in lobbying dynamics following a focusing event, the responsiveness of organisations and political gatekeepers to external shocks, and the role of timing in lobbying. We address our bottom-up sampling approach, draw lessons from the implementation of a second survey wave and provide an overview of survey items. We hope that this forum article is useful for scholars aiming to use our dataset and those starting new data collection efforts. [ABSTRACT FROM AUTHOR]

• In-depth survey on recent handwritten mathematical expression recognition methods. • Paradigm shift from grammar/graph-based parsing to DNN models with attention. • Comparisons of the methods on open datasets and discussions of their pros and cons. • Reviewing the progress and presenting remaining challenges. Recognition of handwritten mathematical expressions (HMEs) has attracted growing interest due to steady progress in handwriting recognition techniques and the rapid emergence of pen- and touch-based devices. Math formula recognition may be understood as a generalization of text recognition: formulas represent mathematical statements using a two dimensional arrangement of symbols on writing lines that are organized hierarchically. This survey provides an overview of techniques published in the last decade, including those taking input from handwritten strokes (i.e., 'online', as captured by a pen/touch device), raster images (i.e., 'offline,' from pixels), or both. Traditionally, HMEs were recognized by performing four structural pattern recognition tasks in separate steps: (1) symbol segmentation, (2) symbol classification, (3) spatial relationship classification, and (4) structural analysis, which identifies the arrangement of symbols on writing lines (e.g., in a Symbol Layout Tree (SLT) or LaTeX string). Recently, encoder–decoder neural network models and Graph Neural Network (GNN) approaches have greatly increased HME recognition accuracy. These newer approaches perform all recognition tasks simultaneously, and utilize contextual features across tasks (e.g., using neural self-attention models). We also discuss evaluation techniques and benchmarks, and explore some implicit dependencies among the four key recognition tasks. Finally, we identify limitations of current systems, and present suggestions for future work, such as using two-dimensional language models rather than the one-dimensional models commonly used in encoder–decoder models. [ABSTRACT FROM AUTHOR]

It is crucial to implement innovative artificial intelligence (AI)-powered network intrusion detection systems (NIDSes) to protect enterprise networks from cyberattacks, which have recently become more diverse and sophisticated. High-quality labeled training datasets are required to train AI-powered NIDSes; such datasets are globally scarce, and generating new training datasets is considered cumbersome. In this study, we investigate the possibility of an approach that integrates the strengths of existing security appliances to generate labeled training datasets that can be leveraged to develop brand-new AI-powered cybersecurity solutions. We begin by locating communication flows that the deployed NIDSes detect as suspicious, investigating their causal factors, and assigning appropriate labels in a universal format. Then, we output the packet data in the identified communication flows and the corresponding alert-type labels as labeled data. We demonstrate the effectiveness of the labeling scheme by evaluating classification models trained with the labeled dataset we generated. Furthermore, we provide case studies to examine the performance of several commonly used NIDSes and on practical approaches to automating the security triage process. Labeled datasets in this study are generated using public datasets and open-source NIDSes to ensure the reproducibility of the results. The datasets and the software tools are made publicly accessible for research use.

This work analyzes a new indoor laboratory dataset looking at early fire indicators in controlled and realistic experiments representing different incipient fire scenarios. The experiments were performed within the constraints of an indoor laboratory setting using multiple distributed sensor nodes in different room positions. Each sensor node collected data of particulate matter (PM), volatile organic compounds (VOCs), carbon monoxide (CO), carbon dioxide (CO2), hydrogen (H2), ultraviolet radiation (UV), air temperature, and humidity in terms of a multivariate time series. These data hold immense value for researchers within the machine learning and data science communities who are keen to explore innovative and advanced statistical and machine learning techniques. They serve as a valuable resource for the development of early fire detection systems. The analysis of the collected data was carried out depending on the Manhattan distance between the fire source and the sensor node. We found that especially larger particles (>0.5 μm) and VOCs show a significant dependency with respect to the intensity as a function of the Manhattan distance to the source. Moreover, we observed differences in the propagation behavior of VOCs, PM, and CO, which are particularly relevant in incipient fire scenarios due to the presence of strand propagation effects.

The thalamus is a subcortical brain structure linked to the motor system. Since certain changes within this structure are related to diseases, such as multiple sclerosis and Parkinson’s, the characterization of the thalamus—e.g., shape assessment—is a crucial step in relevant studies and applications, including medical research and surgical planning. A robust and reliable thalamus-segmentation method is therefore, required to meet these demands. Despite presenting low contrast for this particular structure, T1-weighted imaging is still the most common MRI sequence for thalamus segmentation. However, diffusion MRI (dMRI) captures different micro-structural details of the biological tissue and reveals more contrast of the thalamic borders, thereby serving as a better candidate for thalamus-segmentation methods. Accordingly, we propose a baseline multimodality thalamus-segmentation pipeline that combines dMRI and T1-weighted images within a CNN approach, achieving state-of-the-art levels of Dice overlap. Furthermore, we are hosting an open benchmark with a large, preprocessed, publicly available dataset that includes co-registered, T1-weighted, dMRI, manual thalamic masks; masks generated by three distinct automated methods; and a STAPLE consensus of the masks. The dataset, code, environment, and instructions for the benchmark leaderboard can be found on our GitHub and CodaLab.

Aim: We aimed to develop a new signature based on immune-related genes to predict prognosis and response to immune checkpoint inhibitors in patients with triple-negative breast cancer (TNBC). Materials & methods: Single-sample gene set enrichment was used to develop an immune-based prognostic signature (IPRS) for TNBC patients. We conducted multivariate Cox analysis to evaluate the prognosis value of the IPRS. Result: An IPRS based on 66 prognostic genes was developed. Multivariate Cox analysis indicated that the IPRS was an independent factor for prognosis. PD-1, PD-L1, PD-L2 and CTLA4 gene expression was higher in the low-risk group, suggesting IPRS could predict the response to immune checkpoint inhibitors. Conclusion: The IPRS might be a reliable signature to predict TNBC patients' prognosis and response to immune checkpoint inhibitors, but needs prospective validation. [ABSTRACT FROM AUTHOR]

Pedestrian navigation activity recognition (PNAR) has a significant impact on positioning and tracking performance. Smartphone-based PNAR utilizes measurements from sensors embedded in smartphone to identify pedestrian motion mode and smartphone usage mode. Compared with other PNAR technologies, smartphone-based PNAR has the advantage of autonomy and practicality. Though various PNAR recognition methods based on smartphone have been proposed, up-to-date review papers that summarize relevant technologies, methods, and solutions of PNAR are relatively less so far in the literature. This work aims to present an elaborated, timely, and valuable survey for different smartphone-based PNAR techniques, including sensor calibration, pedestrian modeling, pedestrian motion and smartphone usage modes definition, workflow, state-of-the-art research methods, public datasets, performance evaluation metrics, and relative competitions. Finally, applications, current challenges and future research trends are discussed. The work propels a better understanding of existing navigation activity recognition methods. It is helpful for researchers to further design PNAR methods, and develop more accurate and robust pedestrian positioning and navigation systems. [ABSTRACT FROM AUTHOR]

The target detection algorithm based on supervised learning is the current mainstream algorithm for target detection. A high-quality dataset is the prerequisite for the target detection algorithm to obtain good detection performance. The larger the number and quality of the dataset, the stronger the generalization ability of the model, that is, the dataset determines the upper limit of the model learning. The convolutional neural network optimizes the network parameters in a strong supervision method. The error is calculated by comparing the predicted frame with the manually labeled real frame, and then the error is passed into the network for continuous optimization. Strongly supervised learning mainly relies on a large number of images as models for continuous learning, so the number and quality of images directly affect the results of learning. This paper proposes a dataset STAR-24K (meaning a dataset for Space TArget Recognition with more than 24,000 images) for detecting common targets in space. Since there is currently no publicly available dataset for space target detection, we extracted some pictures from a series of channels such as pictures and videos released by the official websites of NASA (National Aeronautics and Space Administration) and ESA (The European Space Agency) and expanded them to 24,451 pictures. We evaluate popular object detection algorithms to build a benchmark. Our STAR-24K dataset is publicly available at https://github.com/Zzz-zcy/STAR-24K. [ABSTRACT FROM AUTHOR]

The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field. [ABSTRACT FROM AUTHOR]

Concealed objects detection in terahertz imaging is an urgent need for public security and counter-terrorism. So far, there is no public terahertz imaging dataset for the evaluation of objects detection algorithms. This paper provides a public dataset for evaluating multi-object detection algorithms in active terahertz imaging. Due to high sample similarity and poor imaging quality, object detection on this dataset is much more difficult than on those commonly used public object detection datasets in the computer vision field. Since the traditional hard example mining approach is designed based on the two-stage detector and cannot be directly applied to the one-stage detector, this paper designs an image-based Hard Example Mining (HEM) scheme based on RetinaNet. Several state-of-the-art detectors, including YOLOv3, YOLOv4, FRCN-OHEM, and RetinaNet, are evaluated on this dataset. Experimental results show that the RetinaNet achieves the best mAP and HEM further enhances the performance of the model. The parameters affecting the detection metrics of individual images are summarized and analyzed in the experiments. [ABSTRACT FROM AUTHOR]

Over the recent years, deep-learning technology has been widely used. However, in research based on Synthetic Aperture Radar (SAR) ship target detection, it is difficult to support the training of a deep-learning network model because of the difficulty in data acquisition and the small scale of the samples. This paper provides a SAR ship detection dataset with a high resolution and large-scale images. This dataset comprises 31 images from Gaofen-3 satellite SAR images, including harbors, islands, reefs, and the sea surface in different conditions. The backgrounds include various scenarios such as the near shore and open sea. We conducted experiments using both traditional detection algorithms and deep-learning algorithms and observed the densely connected end-to-end neural network to achieve the highest average precision of 88.1%. Based on the experiments and performance analysis, corresponding benchmarks are provided as a basis for further research on SAR ship detection using this dataset.

Objective. This study aims to address the challenges associated with data-driven electroencephalography (EEG) data analysis by introducing a standardised library called BIDSAlign . This library efficiently processes and merges heterogeneous EEG datasets from different sources into a common standard template. The goal of this work is to create an environment that allows to preprocess public datasets in order to provide data for the effective training of deep learning (DL) architectures. Approach. The library can handle both Brain Imaging Data Structure (BIDS) and non-BIDS datasets, allowing the user to easily preprocess multiple public datasets. It unifies the EEG recordings acquired with different settings by defining a common pipeline and a specified channel template. An array of visualisation functions is provided inside the library, together with a user-friendly graphical user interface to assist non-expert users throughout the workflow. Main results. BIDSAlign enables the effective use of public EEG datasets, providing valuable medical insights, even for non-experts in the field. Results from applying the library to datasets from OpenNeuro demonstrate its ability to extract significant medical knowledge through an end-to-end workflow, facilitating group analysis, visual comparison and statistical testing. Significance. BIDSAlign solves the lack of large EEG datasets by aligning multiple datasets to a standard template. This unlocks the potential of public EEG data for training DL models. It paves the way to promising contributions based on DL to clinical and non-clinical EEG research, offering insights that can inform neurological disease diagnosis and treatment strategies., (Creative Commons Attribution license.)

Measuring and adjusting the training load is essential in resistance training, as training overload can increase the risk of injuries. At the same time, too little load does not deliver the desired training effects. Usually, external load is quantified using objective measurements, such as lifted weight distributed across sets and repetitions per exercise. Internal training load is usually assessed using questionnaires or ratings of perceived exertion (RPE). A standard RPE scale is the Borg scale, which ranges from 6 (no exertion) to 20 (the highest exertion ever experienced). Researchers have investigated predicting RPE for different sports using sensor modalities and machine learning methods, such as Support Vector Regression or Random Forests. This paper presents PERSIST, a novel dataset for predicting PERceived exertion during reSIStance Training. We recorded multiple sensor modalities simultaneously, including inertial measurement units (IMU), electrocardiography (ECG), and motion capture (MoCap). The MoCap data has been synchronized to the IMU and ECG data. We also provide heart rate variability (HRV) parameters obtained from the ECG signal. Our dataset contains data from twelve young and healthy male participants with at least one year of resistance training experience. Subjects performed twelve sets of squats on a Flywheel platform with twelve repetitions per set. After each set, subjects reported their current RPE. We chose the squat exercise as it involves the largest muscle group. This paper demonstrates how to access the dataset. We further present an exploratory data analysis and show how researchers can use IMU and ECG data to predict perceived exertion.

This paper presents a digital image dataset of historical handwritten birth records stored in the archives of several parishes across Sweden, together with the corresponding metadata that supports the evaluation of document analysis algorithms' performance. The dataset is called SHIBR (the Swedish Historical Birth Records). The contribution of this paper is twofold. First, we believe it is the first and the largest Swedish dataset of its kind provided as open access (15,000 high-resolution colour images of the era between 1800 and 1840). We also perform some data mining of the dataset to uncover some statistics and facts that might be of interest and use to genealogists. Second, we provide a comprehensive survey of contemporary datasets in the field that are open to the public along with a compact review of word spotting techniques. The word transcription file contains 17 columns of information pertaining to each image (e.g., child's first name, birth date, date of baptism, father's first/last name, mother's first/last name, death records, town, job title of the father/mother, etc.). Moreover, we evaluate some deep learning models, pre-trained on two other renowned datasets, for word spotting in SHIBR. However, our dataset proved challenging due to the unique handwriting style. Therefore, the dataset could also be used for competitions dedicated to a large set of document analysis problems, including word spotting. [ABSTRACT FROM AUTHOR]

Purpose: To advance fair and consistent comparisons of dose prediction methods for knowledge‐based planning (KBP) in radiation therapy research. Methods: We hosted OpenKBP, a 2020 AAPM Grand Challenge, and challenged participants to develop the best method for predicting the dose of contoured computed tomography (CT) images. The models were evaluated according to two separate scores: (a) dose score, which evaluates the full three‐dimensional (3D) dose distributions, and (b) dose‐volume histogram (DVH) score, which evaluates a set DVH metrics. We used these scores to quantify the quality of the models based on their out‐of‐sample predictions. To develop and test their models, participants were given the data of 340 patients who were treated for head‐and‐neck cancer with radiation therapy. The data were partitioned into training (n=200), validation (n=40), and testing (n=100) datasets. All participants performed training and validation with the corresponding datasets during the first (validation) phase of the Challenge. In the second (testing) phase, the participants used their model on the testing data to quantify the out‐of‐sample performance, which was hidden from participants and used to determine the final competition ranking. Participants also responded to a survey to summarize their models. Results: The Challenge attracted 195 participants from 28 countries, and 73 of those participants formed 44 teams in the validation phase, which received a total of 1750 submissions. The testing phase garnered submissions from 28 of those teams, which represents 28 unique prediction methods. On average, over the course of the validation phase, participants improved the dose and DVH scores of their models by a factor of 2.7 and 5.7, respectively. In the testing phase one model achieved the best dose score (2.429) and DVH score (1.478), which were both significantly better than the dose score (2.564) and the DVH score (1.529) that was achieved by the runner‐up models. Lastly, many of the top performing teams reported that they used generalizable techniques (e.g., ensembles) to achieve higher performance than their competition. Conclusion: OpenKBP is the first competition for knowledge‐based planning research. The Challenge helped launch the first platform that enables researchers to compare KBP prediction methods fairly and consistently using a large open‐source dataset and standardized metrics. OpenKBP has also democratized KBP research by making it accessible to everyone, which should help accelerate the progress of KBP research. The OpenKBP datasets are available publicly to help benchmark future KBP research. [ABSTRACT FROM AUTHOR]

Compared with the traditional neurofeedback paradigm, the cognition-guided neurofeedback brain–computer interface (BCI) is a novel paradigm with significant effect on nicotine addiction. However, the cognition-guided neurofeedback BCI dataset is extremely lacking at present. This paper provides a BCI dataset based on a novel cognition-guided neurofeedback on nicotine addiction. Twenty-eight participants are recruited and involved in two visits of neurofeedback training. This cognition-guided neurofeedback includes two phases: an offline classifier construction and a real-time neurofeedback training. The original electroencephalogram (EEG) raw data of two phases are provided and evaluated in this paper. The event-related potential (ERP) amplitude and channel waveform suggest that our BCI dataset is of good quality and consistency. During neurofeedback training, the participants’ smoking cue reactivity patterns have a significant reduction. The mean accuracy of the multivariate pattern analysis (MVPA) classifier can reach approximately 70%. This novel cognition-guided neurofeedback BCI dataset can be used to develop comparisons with other neurofeedback systems and provide a reference for the development of other BCI algorithms and neurofeedback paradigms on addiction.

Research on pre-impact fall detection with wearable inertial sensors (detecting fall accidents prior to body-ground impacts) has grown rapidly in the past decade due to its great potential for developing an on-demand fall-related injury prevention system. However, most researchers use their own datasets to develop fall detection algorithms and rarely make these datasets publicly available, which poses a challenge to fairly evaluate the performance of different algorithms on a common basis. Even though some open datasets have been established recently, most of them are impractical for pre-impact fall detection due to the lack of temporal labels for fall time and limited types of motions. In order to overcome these limitations, in this study, we proposed and publicly provided a large-scale motion dataset called “KFall,” which was developed from 32 Korean participants while wearing an inertial sensor on the low back and performing 21 types of activities of daily living and 15 types of simulated falls. In addition, ready-to-use temporal labels of the fall time based on synchronized motion videos were published along with the dataset. Those enhancements make KFall the first public dataset suitable for pre-impact fall detection, not just for post-fall detection. Importantly, we have also developed three different types of latest algorithms (threshold based, support-vector machine, and deep learning), using the KFall dataset for pre-impact fall detection so that researchers and practitioners can flexibly choose the corresponding algorithm. Deep learning algorithm achieved both high overall accuracy and balanced sensitivity (99.32%) and specificity (99.01%) for pre-impact fall detection. Support vector machine also demonstrated a good performance with a sensitivity of 99.77% and specificity of 94.87%. However, the threshold-based algorithm showed relatively poor results, especially the specificity (83.43%) was much lower than the sensitivity (95.50%). The performance of these algorithms could be regarded as a benchmark for further development of better algorithms with this new dataset. This large-scale motion dataset and benchmark algorithms could provide researchers and practitioners with valuable data and references to develop new technologies and strategies for pre-impact fall detection and proactive injury prevention for the elderly.

Research on pre-impact fall detection with wearable inertial sensors (detecting fall accidents prior to body-ground impacts) has grown rapidly in the past decade due to its great potential for developing an on-demand fall-related injury prevention system. However, most researchers use their own datasets to develop fall detection algorithms and rarely make these datasets publicly available, which poses a challenge to fairly evaluate the performance of different algorithms on a common basis. Even though some open datasets have been established recently, most of them are impractical for pre-impact fall detection due to the lack of temporal labels for fall time and limited types of motions. In order to overcome these limitations, in this study, we proposed and publicly provided a large-scale motion dataset called "KFall," which was developed from 32 Korean participants while wearing an inertial sensor on the low back and performing 21 types of activities of daily living and 15 types of simulated falls. In addition, ready-to-use temporal labels of the fall time based on synchronized motion videos were published along with the dataset. Those enhancements make KFall the first public dataset suitable for pre-impact fall detection, not just for post-fall detection. Importantly, we have also developed three different types of latest algorithms (threshold based, support-vector machine, and deep learning), using the KFall dataset for pre-impact fall detection so that researchers and practitioners can flexibly choose the corresponding algorithm. Deep learning algorithm achieved both high overall accuracy and balanced sensitivity (99.32%) and specificity (99.01%) for pre-impact fall detection. Support vector machine also demonstrated a good performance with a sensitivity of 99.77% and specificity of 94.87%. However, the threshold-based algorithm showed relatively poor results, especially the specificity (83.43%) was much lower than the sensitivity (95.50%). The performance of these algorithms could be regarded as a benchmark for further development of better algorithms with this new dataset. This large-scale motion dataset and benchmark algorithms could provide researchers and practitioners with valuable data and references to develop new technologies and strategies for pre-impact fall detection and proactive injury prevention for the elderly. [ABSTRACT FROM AUTHOR]

Compared with the traditional neurofeedback paradigm, the cognition-guided neurofeedback brain–computer interface (BCI) is a novel paradigm with significant effect on nicotine addiction. However, the cognition-guided neurofeedback BCI dataset is extremely lacking at present. This paper provides a BCI dataset based on a novel cognition-guided neurofeedback on nicotine addiction. Twenty-eight participants are recruited and involved in two visits of neurofeedback training. This cognition-guided neurofeedback includes two phases: an offline classifier construction and a real-time neurofeedback training. The original electroencephalogram (EEG) raw data of two phases are provided and evaluated in this paper. The event-related potential (ERP) amplitude and channel waveform suggest that our BCI dataset is of good quality and consistency. During neurofeedback training, the participants' smoking cue reactivity patterns have a significant reduction. The mean accuracy of the multivariate pattern analysis (MVPA) classifier can reach approximately 70%. This novel cognition-guided neurofeedback BCI dataset can be used to develop comparisons with other neurofeedback systems and provide a reference for the development of other BCI algorithms and neurofeedback paradigms on addiction. [ABSTRACT FROM AUTHOR]

• A deep learning approach is proposed to perform the cross-session hand gesture recognition task using sEMG signals. • The proposed model uses a multi-layer CNN with multi-attention as the feature extractor for automatic feature extraction. • The multi-attention consists of channel attention, spatial attention, and temporal attention. • The performance of the proposed method is evaluated on two public datasets. Electromyographic hand gesture recognition can be used to develop myoelectric prosthetic hands for disabled people when the acquired myoelectric signals are accurately classified. Recently, the developed end-to-end deep learning methods are widely used in hand gesture recognition for their automatic extraction of features from raw signals. But not all extracted features are useful and unimportant information can impede gesture recognition. In this study, a deep learning model using multi-attention for electromyographic hand gesture recognition is proposed. The attention mechanism inspired by the biological system enables deep learning models to focus on the important parts of input data while ignoring unimportant information. At first, a convolutional neural network is employed as the feature extractor, enabling the learning of high-level discriminative features from input signals. Then, multi-attention blocks, including channel attention, spatial attention, and temporal attention, are integrated into the convolutional layers, enhancing the extraction of pertinent features by emphasizing critical information through weight recalibration. Finally, the proposed model is evaluated on both the public NinaPro dataset and the public Myo dataset, demonstrating superior performance compared to baseline models in terms of recognition accuracy. The experimental results reveal that the model with attention mechanism achieves an average recognition accuracy of 91.64%, representing a 1.1% improvement over the model without attention mechanism. [ABSTRACT FROM AUTHOR]

An Electrical Submersible Pump (ESP) is an important equipment used in the industry for lifting liquids in various types of wells. An ESP is widely used in the oil industry for offshore exploration. Detecting a faulty ESP before installation is a predictive maintenance measure in order to extend its operational time. Machine learning fault diagnosis is an effective way for performing this task. Machine learning fault diagnosis algorithms are highly dependent of the availability of an appropriate problem dataset. This paper describes in detail the problem of ESP fault diagnosis and the ESPset dataset, a real-world and public dataset for vibration-based fault diagnosis of electrical submersible pumps used on offshore oil exploration. In addition, the paper also proposes an experimental framework for adequately comparing research works based on the ESPset dataset and defines benchmark classifiers and respective results as referential to the fault diagnosis research community. The framework considers the fact that some subset of samples are not drawn independently, and therefore, proposes a cross-validation sampling strategy that mitigates the similarity bias among samples. Indeed, this work shows that a conventional k-fold cross-validation may lead to a clear overestimation of the average performance. This fact is supported by results which show that the best classification model drops from a mean F-measure of 0.887 to 0.733 when removing the similarity bias from the data. • The Electrical Submersible Pumps (ESP) fault diagnosis problem description: a broader and detailed specification. • The ESPset vibration dataset is published: 6032 instances of ESP vibration tests. • An experimental framework to avoid dependence between the training and test phases of the learning task. • The ESPset benchmark classifiers are presented. • The results of the experimental study using the proposed framework and the benchmark classifiers are shown. [ABSTRACT FROM AUTHOR]

We construct a public dataset for WiFi-based Activity Recognition named WiAR with sixteen activities operated by ten volunteers in three indoor environments. It aims to provide public signal data for researchers to reduce the cost of collected signal data and conveniently evaluate the performance of WiFi-based human activity recognition in different domains. First, we introduce the basic knowledge of WiFi signals regarding RSSI, CSI, and wireless hardware. Second, we explain the characteristics of WiAR dataset in terms of activities types, data format, data acquisition ways, and influence factors. Third, the proposed framework can estimate the quality of the shared signal data provided by other peers. Finally, we select and use five classification algorithms and two deep learning algorithms to evaluate the performance of WiAR dataset on human activity recognition. The results show that the accuracy of WiAR dataset is higher than 80% using machine learning algorithms and 90% using deep learning algorithms in different indoor environments.

Featured Application: This dataset can be used for supervised training of models for colorectal polyp detection, localisation, segmentation and classification. Colorectal cancer is one of the world leading death causes. Fortunately, an early diagnosis allows for effective treatment, increasing the survival rate. Deep learning techniques have shown their utility for increasing the adenoma detection rate at colonoscopy, but a dataset is usually required so the model can automatically learn features that characterize the polyps. In this work, we present the PICCOLO dataset, that comprises 3433 manually annotated images (2131 white-light images 1302 narrow-band images), originated from 76 lesions from 40 patients, which are distributed into training (2203), validation (897) and test (333) sets assuring patient independence between sets. Furthermore, clinical metadata are also provided for each lesion. Four different models, obtained by combining two backbones and two encoder–decoder architectures, are trained with the PICCOLO dataset and other two publicly available datasets for comparison. Results are provided for the test set of each dataset. Models trained with the PICCOLO dataset have a better generalization capacity, as they perform more uniformly along test sets of all datasets, rather than obtaining the best results for its own test set. This dataset is available at the website of the Basque Biobank, so it is expected that it will contribute to the further development of deep learning methods for polyp detection, localisation and classification, which would eventually result in a better and earlier diagnosis of colorectal cancer, hence improving patient outcomes. [ABSTRACT FROM AUTHOR]

Purpose: To advance research in the field of machine learning for MR image reconstruction with an open challenge. Methods: We provided participants with a dataset of raw k‐space data from 1,594 consecutive clinical exams of the knee. The goal of the challenge was to reconstruct images from these data. In order to strike a balance between realistic data and a shallow learning curve for those not already familiar with MR image reconstruction, we ran multiple tracks for multi‐coil and single‐coil data. We performed a two‐stage evaluation based on quantitative image metrics followed by evaluation by a panel of radiologists. The challenge ran from June to December of 2019. Results: We received a total of 33 challenge submissions. All participants chose to submit results from supervised machine learning approaches. Conclusions: The challenge led to new developments in machine learning for image reconstruction, provided insight into the current state of the art in the field, and highlighted remaining hurdles for clinical adoption. [ABSTRACT FROM AUTHOR]

This paper reports on a benchmark dataset acquired with a brain–computer interface (BCI) system based on the rapid serial visual presentation (RSVP) paradigm. The dataset consists of 64-channel electroencephalogram (EEG) data from 64 healthy subjects (sub1,…, sub64) while they performed a target image detection task. For each subject, the data contained two groups (“A” and “B”). Each group contained two blocks, and each block included 40 trials that corresponded to 40 stimulus sequences. Each sequence contained 100 images presented at 10 Hz (10 images per second). The stimulus images were street-view images of two categories: target images with human and non-target images without human. Target images were presented randomly in the stimulus sequence with a probability of 1∼4%. During the stimulus presentation, subjects were asked to search for the target images and ignore the non-target images in a subjective manner. To keep all original information, the dataset was the raw continuous data without any processing. On one hand, the dataset can be used as a benchmark dataset to compare the algorithms for target identification in RSVP-based BCIs. On the other hand, the dataset can be used to design new system diagrams and evaluate their BCI performance without collecting any new data through offline simulation. Furthermore, the dataset also provides high-quality data for characterizing and modeling event-related potentials (ERPs) and steady-state visual evoked potentials (SSVEPs) in RSVP-based BCIs. The dataset is freely available from http://bci.med.tsinghua.edu.cn/download.html.

With recent advances in learning algorithms and hardware development, autonomous cars have shown promise when operating in structured environments under good driving conditions. However, for complex, cluttered, and unseen environments with high uncertainty, autonomous driving systems still frequently demonstrate erroneous or unexpected behaviors that could lead to catastrophic outcomes. Autonomous vehicles should ideally adapt to driving conditions; while this can be achieved through multiple routes, it would be beneficial as a first step to be able to characterize driveability in some quantified form. To this end, this paper aims to create a framework for investigating different factors that can impact driveability. Also, one of the main mechanisms to adapt autonomous driving systems to any driving condition is to be able to learn and generalize from representative scenarios. The machine learning algorithms that currently do so learn predominantly in a supervised manner and consequently need sufficient data for robust and efficient learning. Therefore, we also perform a comparative overview of 54 public driving datasets that enable learning and publish this dataset index at https://sites.google.com/view/driveability-survey-datasets. Specifically, we categorize the datasets according to the use cases and highlight the datasets that capture the complicated and hazardous driving conditions, which can be better used for training robust driving models. Furthermore, by discussions of what driving scenarios are not covered by the existing public datasets and what driveability factors need more investigation and data acquisition, this paper aims to encourage both targeted dataset collection and the proposal of novel driveability metrics that enhance the robustness of autonomous cars in adverse environments. [ABSTRACT FROM AUTHOR]

A population group that is often overlooked in the recent revolution of self-tracking is the group of older people. This growing proportion of the general population is often faced with increasing health issues and discomfort. In order to come up with lifestyle advice towards the elderly, we need the ability to quantify their lifestyle, before and after an intervention. This research focuses on the task of activity recognition (AR) from accelerometer data. With that aim, we collect a substantial labelled dataset of older individuals wearing multiple devices simultaneously and performing a strict protocol of 16 activities (the GOTOV dataset, N = 28 ). Using this dataset, we trained Random Forest AR models, under varying sensor set-ups and levels of activity description granularity. The model that combines ankle and wrist accelerometers (GENEActiv) produced the best results (accuracy > 80 % ) for 16-class classification. At the same time, when additional physiological information is used, the accuracy increased ( > 85 % ). To further investigate the role of granularity in our predictions, we developed the LARA algorithm, which uses a hierarchical ontology that captures prior biological knowledge to increase or decrease the level of activity granularity (merge classes). As a result, a 12-class model in which the different paces of walking were merged showed a performance above 93 % . Testing this 12-class model in labelled free-living pilot data, the mean balanced accuracy appeared to be reasonably high, while using the LARA algorithm, we show that a 7-class model (lying down, sitting, standing, household, walking, cycling, jumping) was optimal for accuracy and granularity. Finally, we demonstrate the use of the latter model in unlabelled free-living data from a larger lifestyle intervention study. In this paper, we make the validation data as well as the derived prediction models available to the community. [ABSTRACT FROM AUTHOR]

This work proposes a new clustering algorithm named FINFCM by converting original data into fuzzy interval number (FIN) firstly, then it proofs F that denotes the collection of FINs is a lattice and introduce a novel metric distance based on the results from lattice theory as well as combining them with Fuzzy c-means clustering. The relevant mathematical background about lattice theory and the specific procedure which is used to construct FIN have been presented in this paper. Three evaluation indexes including Compactness, RandIndex and Precision are applied to evaluate the performance of FINFCM, FCM and HC algorithm in four experiments used UCI public datasets. The FINFCM algorithm has shown better clustering performance compared to other traditional clustering algorithms and the results are also discussed specifically. [ABSTRACT FROM AUTHOR]