Additional Contextual Information Research Articles

Robust vision detection of pipeline solder joints

Purpose Solder joint inspection plays a critical role in various industries, with a focus on integrated chip (IC) solder joints and metal surface welds. However, the detection of tubular solder joints has received relatively less attention. This paper aims to address the challenges of detecting small targets and complex environments by proposing a robust visual detection method for pipeline solder joints. The method is characterized by its simplicity, cost-effectiveness and ease of implementation. Design/methodology/approach A robust visual detection method based on the characteristics of pipeline solder joints is proposed. With the improved hue, saturation and value (HSV) color space, the method uses a multi-level template matching approach to first segment the pipeline from the background, and then match the endpoint of the pipeline to accurately locate the solder joint. The proposed method leverages the distinctive characteristics of pipeline solder joints and employs an enhanced HSV color space. A multi-level template matching approach is utilized to segment the pipeline from the background and accurately locate the solder joint by matching the pipeline endpoint. Findings The experimental results demonstrate the effectiveness of the proposed solder joint detection method in practical detection tasks. The average precision of pipeline weld joint localization exceeds 95%, while the average recall is greater than 90%. These findings highlight the applicability of the method to pipeline solder joint detection tasks, specifically in the context of production lines for refrigeration equipment. Research limitations/implications The precision of the method is influenced by the placement angle and lighting conditions of the test specimen, which may pose challenges and impact the algorithm's performance. Potential avenues for improvement include exploring deep learning methods, incorporating additional features and contextual information for localization, and utilizing advanced image enhancement techniques to improve image quality. Originality/value The proposed pipeline solder joint detection method offers a novel and practical approach. The simplicity, cost-effectiveness and ease of implementation make it an attractive choice for detecting pipeline solder joints in different industrial applications.

Speaking the Same Language - The Development of a Glossary of Terms for Social Prescribing in Wales.

Social prescribing can facilitate the integration of health, social care and community support but has a diverse and confusing terminology that impairs cross-sectoral communication and creates barriers to engagement. To address this issue a mixed-methods approach that incorporated a scoping review, a group concept mapping study and consultation was employed to identify and classify the terminology associated with social prescribing. The findings were then used to inform the development of a glossary of terms for social prescribing. Many terms are used interchangeably to describe the same specific aspects of social prescribing. Much of the terminology originates from the health and social care literature of England. The terminology used in the academic literature may not accurately reflect the terminology used by the social prescribing workforce. The innovative and interactive glossary of terms identifies the terminology associated with social prescribing and provides additional contextual information. The process of developing the dual language glossary presented several considerations and challenges. The glossary of terms will facilitate cross-sector communication and reduce barriers to engagement with social prescribing. It takes an important first step to help clarify and standardise the language associated with social prescribing, for professionals and members of the public alike.

Location Based Privacy Preserving using Machine Learning

Location-based privacy preservation is crucial in the digital age due to the widespread use of location-based services and growing concerns about individual privacy. Despite the use of k-anonymity measures, current systems face challenges, particularly the risk of re-identification, especially when attackers have additional contextual information. These systems also suffer from information loss, leading to a significant decrease in data utility. Striking the right balance between privacy and data utility remains a prominent challenge in the field of location-based privacy preservation. To address the existing gaps and challenges in privacy-preserving location data publishing, a robust framework termed Location anonymization framework is being introduced which consists of three methods Generalization, Sequence alignment and Clustering. DGH Trees are being used to minimize the information loss and also maintains a balance between privacy and utility. To enhance privacy preservation in overly sensitive datasets, a modified version of the k-means algorithm is being put forth. Moreover, to improve the alignment process, the more efficient iterative multisequence alignment is being opted for over the progressive counterpart within this framework. The aim is to achieve a more balanced trade-off between privacy and utility in location data publishing.

Research on multi-object detection technology for road scenes based on SDG-YOLOv5

To resolve the challenges of low detection accuracy and inadequate real-time performance in road scene detection, this article introduces the enhanced algorithm SDG-YOLOv5. The algorithm incorporates the SIoU Loss function to accurately predict the angle loss of bounding boxes, ensuring their directionality during regression and improving both regression accuracy and convergence speed. A novel lightweight decoupled heads (DHs) approach is employed to separate the classification and regression tasks, thereby avoiding conflicts between their focus areas. Moreover, the Global Attention Mechanism Group Convolution (GAMGC), a lightweight strategy, is utilized to enhance the network’s capability to process additional contextual information, thereby improving the detection of small targets. Extensive experimental analysis on datasets from Udacity Self Driving Car, BDD100K, and KITTI demonstrates that the proposed algorithm achieves improvements in mAP@.5 of 2.2%, 3.4%, and 1.0% over the original YOLOv5, with a detection speed of 30.3 FPS. These results illustrate that the SDG-YOLOv5 algorithm effectively addresses both detection accuracy and real-time performance in road scene detection.

Center-bridged Interaction Fusion for hyperspectral and LiDAR classification

Recent classifications in Earth Observation (EO) commonly involve a combination of Hyperspectral Image (HSI) and Light Detection and Ranging (LiDAR) signals. However, many current methods fail to consider the HSI-LiDAR information concurrently, especially in terms of both its intra- and inter-modality aspects. Additionally, current methods are generally limited in their ability to fuse the features extracted from different modalities. Hence, this paper proposes a center-bridged framework, called Interaction Fusion (IF), that can leverage diverse information concerning the intra- and inter-modality relationships at the same time. More specifically, intra- and inter-modality information can be enriched by introducing the center patch of HSI (cp-HSI) as an extra input, This introduces additional contextual information within and across modalities that can be leverage for deeper insights. Further, we propose a fusion matrix as a structural feature map designed to integrate nine views generated by a view generator, enabling the adaptive combination of intra- and inter-modality information. Overall, our approach allows potential patterns to be captured, while mitigating any bias resulting from incomplete information. Extensive experiments conducted on three widely recognized datasets – Trento, MUUFL, and Houston – demonstrate that the IF framework achieves state-of-the-art results, surpassing existing methods.

Multivariate USV Motion Prediction Method Based on a Temporal Attention Weighted TCN-Bi-LSTM Model

Unmanned surface vehicle (USV)’s motion is represented by time-series data that exhibit highly nonlinear and non-stationary features, significantly influenced by environmental factors, such as wind speed and waves, when sailing on the sea. The accurate prediction of USV motion, particularly crucial parameters, such as the roll angle and pitch angle, is imperative for ensuring safe navigation. However, traditional and single prediction models often struggle with low accuracy and fail to capture the intricate spatial–temporal dependencies among multiple input variables. To address these limitations, this paper proposes a prediction approach integrating temporal convolutional network (TCN) and bi-directional long short-term memory network (Bi-LSTM) models, augmented with a temporal pattern attention (TPA) mechanism, termed the TCN-Bi-LSTM-TPA (TBT) USV motion predictor. This hybrid model effectively combines the strengths of TCN and Bi-LSTM architectures to extract long-term temporal features and bi-directional dependencies. The introduction of the TPA mechanism enhances the model’s capability to extract spatial information, crucial for understanding the intricate interplay of various motion data. By integrating the features extracted by TCN with the output of the attention mechanism, the model incorporates additional contextual information, thereby improving prediction accuracy. To evaluate the performance of the proposed model, we conducted experiments using real USV motion data and calculated four evaluation metrics: mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R-squared (R2). The results demonstrate the superior accuracy of the TCN-Bi-LSTM-TPA hybrid model in predicting USV roll angle and pitch angle, validating its effectiveness in addressing the challenges of multivariate USV motion prediction.

Long-Tailed Effect Study in Remote Sensing Semantic Segmentation Based on Graph Kernel Principles

The performance of semantic segmentation in remote sensing, based on deep learning models, depends on the training data. A commonly encountered issue is the imbalanced long-tailed distribution of data, where the head classes contain the majority of samples while the tail classes have fewer samples. When training with long-tailed data, the head classes dominate the training process, resulting in poorer performance in the tail classes. To address this issue, various strategies have been proposed, such as resampling, reweighting, and transfer learning. However, common resampling methods suffer from overfitting to the tail classes while underfitting the head classes, and reweighting methods are limited in the extreme imbalanced case. Additionally, transfer learning tends to transfer patterns learned from the head classes to the tail classes without rigorously validating its generalizability. These methods often lack additional information to assist in the recognition of tail class objects, thus limiting performance improvements and constraining generalization ability. To tackle the abovementioned issues, a graph neural network based on the graph kernel principle is proposed for the first time. By leveraging the graph kernel, structural information for tail class objects is obtained, serving as additional contextual information beyond basic visual features. This method partially compensates for the imbalance between tail and head class object information without compromising the recognition accuracy of head classes objects. The experimental results demonstrate that this study effectively addresses the poor recognition performance of small and rare targets, partially alleviates the issue of spectral confusion, and enhances the model’s generalization ability.

MRSLN: A Multimodal Residual Speaker-LSTM Network to alleviate the over-smoothing issue for Emotion Recognition in Conversation

Multimodal Emotion Recognition in Conversation (ERC) plays a significant role in the field of human–computer intelligent interaction since it enables computers to perceive and infer the emotions expressed by the individuals, thereby intelligently responding to them. Most of current ERC methods pay more attention to modeling the complex interaction between different modalities. However, the features extracted by their unimodal networks are over-smoothed and may contain insufficient intra-speaker contextual information, which results in suboptimal results. In this paper, we focus on the unimodal learning and propose a simple late fusion framework named Multimodal Residual Speaker-LSTM Network (MRSLN), which uses speaker information to directly model inter-speaker and intra-speaker dependency, rather than fuse it into the learned features. MRSLN uses the speaker-LSTM consisting of the inter-speaker LSTM, intra-speaker LSTM, and the residual network between the input and output of the inter-speaker LSTM. Our proposed method can alleviate the issue of over-smoothing in deep Long Short Term Memory (LSTM) network and also incorporate additional intra-speaker contextual information. Extensive experiments conducted on IEMOCAP and MELD datasets demonstrate that MRSLN effectively captures inter-speaker and intra-speaker information and outperforms currently complex state-of-the-art (SOTA) models in efficiency and classification performance.

A combination of multi‐scale and attention based on the U‐shaped network for retinal vessel segmentation

AbstractAutomated partitioning of retinal vessels depicted in fundus images is beneficial in the detection of specific ailments like hypertension and diabetes. However, retinal vessel images have the problems of a large semantic range, more spatial detail, and limited differentiation among the blood vessels and surroundings, which make vessel segmentation challenging. To overcome these obstacles, we designed a new U‐shaped network named SMP‐Net. First, we propose the sequencer‐convolution (SC) module to obtain the ability to extract both local and global features, thereby improving segmentation accuracy. The SC module is used to filter out shallow noise and enable the fusion of deep and shallow features in the maximum skip connection of the U‐shaped network. Then, the residual multi‐kernel pooling (MP) module is designed to obtain additional contextual information while also mitigating the loss of spatial information caused by constant pooling and convolution to improve vessel coherence. Finally, the pixel attention (PA) module redistributes the weight of each pixel using an element‐wise product multiplication operation. This increases the weight of the vascular feature pixels and improves the ability to identify blood vessels in blurred backgrounds. The proposed method has been demonstrated to be effective through sufficient experimentation on publicly available retinal datasets such as DRIVE, STARE, and CHASE_DB1.

JointTracker: Real-time inertial kinematic chain tracking with joint position estimation

In-field human motion capture (HMC) is drawing increasing attention due to the multitude of application areas. Plenty of research is currently invested in camera-based (markerless) HMC, with the advantage of no infrastructure being required on the body, and additional context information being available from the surroundings. However, the inherent drawbacks of camera-based approaches are the limited field of view and occlusions. In contrast, inertial HMC (IHMC) does not suffer from occlusions, thus being a promising approach for capturing human motion outside the laboratory. However, one major challenge of such methods is the necessity of spatial registration. Typically, during a predefined calibration sequence, the orientation and location of each inertial sensor are registered with respect to the underlying skeleton model. This work contributes to calibration-free IHMC, as it proposes a recursive estimator for the simultaneous online estimation of all sensor poses and joint positions of a kinematic chain model like the human skeleton. The full derivation from an optimization objective is provided. The approach can directly be applied to a synchronized data stream from a body-mounted inertial sensor network. Successful evaluations are demonstrated on noisy simulated data from a three-link chain, real lower-body walking data from 25 young, healthy persons, and walking data captured from a humanoid robot. The estimated and derived quantities, global and relative sensor orientations, joint positions, and segment lengths can be exploited for human motion analysis and anthropometric measurements, as well as in the context of hybrid markerless visual-inertial HMC.

Should carbohydrate-modified diets be the first option for weight loss in people with impaired glucose metabolism? A scoping review.

While the "precision nutrition" movement is at an early stage of development, several investigations have compared low-fat versus carbohydrate (CHO)-modified diets (i.e., low-or-reduced-CHO, low glycemic index/load diets, and high-fiber) in people with normal versus impaired glucose metabolism. The purpose of this scoping review was to summarize evidence in support of the hypothesis that CHO-modified diets are more effective for weight loss among people with impaired glucose metabolism. Fifteen articles were included in this review: seven retrospective analyses of randomized clinical trials and eight prospective randomized clinical trials with prespecified hypotheses related to a diet (low-fat vs. CHO-modified) × phenotype (normal vs. impaired) interaction. Evidence in support of the hypothesis was identified in six of seven retrospective and three of eight prospective studies, which led to a recommendation of CHO-modified diets as a first-line option for people with impaired glucose metabolism. However, the evidence in support of this recommendation is relatively weak, and dietary prescriptions should consider additional contextual information that may influence overall dietary adherence. Additional and rigorous research using innovative randomized experimental approaches is needed for stronger dietary weight loss recommendations based on pretreatment glycemic status.

Facial first impressions following a prison sentence: Negative shift in trait ratings but the same underlying structure

The first impressions we form of unfamiliar others can often guide many important decisions such as whether someone is guilty of a crime or the severity of their sentence, even in the presence of more relevant information. While most of the current work in this context has focused on their impact during trial proceedings and sentencing, little is known about the potential impact of first impressions following a guilty sentence and the success of the subsequent reintegration into society. Here, we used a data-driven approach to address this question by first collecting unconstrained spontaneous impressions from two groups of perceivers – one group believed that the identities they were presented with had received a prison sentence, whereas the other received no additional semantic information (Study 1). This then allowed us to establish the most prevalent traits people refer to when describing their first impressions in this context and to reveal the underlying structure of these impressions using an Exploratory Factor Analysis (Study 2). We find a substantial negative shift in social evaluation following the knowledge of a prison sentence, both in terms of spontaneous descriptions and specific trait ratings. However, this additional contextual information did not affect the underlying structure of first impressions. These findings support social evaluation theories arguing for a more complex interplay between bottom-up visual and top-down semantic or contextual cues during the formation of facial first impressions but also reveal important constraints to the impact of such cues on the core impression formation processes.

Clarification and guidance on the use of the Socio-Economic Impact Classification for Alien Taxa (SEICAT) framework

Understanding the ways in which alien taxa threaten human well-being, beyond purely monetary costs, can be difficult as impacts differ vastly across social, cultural, and economic contexts. Failure to capture impacts outside of monetary costs means that impacts are unfairly weighted towards those that can be easily monetised, which is unlikely to be a realistic measure of how alien species truly affect human well-being. To address this issue, the Socio-Economic Impact Classification for Alien Taxa (SEICAT) was developed with the intention to facilitate standardised classifications and comparisons of the impacts of alien taxa on human well-being and livelihood. The framework measures impacts by assessing to what extent alien taxa have altered human activities, so has application across a broad range of reported impacts associated with different constituents of human well-being. Although in their original paper, Bacher et al. (2018) provided an overview of the SEICAT framework, comprehensive guidelines that enable assessors to overcome potential ambiguities were, until now, unavailable. This may be preventing the broad application of the framework due to reduced usability. Here, we provide clarification and guidance for the application of SEICAT to facilitate standardised, consistent assessments. In particular, we address uncertainties stemming from unclear definitions of impacted communities and activities, as well as the spatial and temporal scales of relevance. We clarify these key issues and give explicit recommendations, whilst encouraging the collection of additional contextual information to be recorded for each assessed impact report, to generate more practical information for end-users of SEICAT data. Further, we recommend adopting an alternative terminology for the impact categories to reduce the potential misuse of the current descriptors. The intended outcome of this work is to aid the broad application of the SEICAT framework in a consistent and transparent manner.

Capturing the patient’s voice to inform advanced clinical decision support for guideline-based cancer symptom management.

510 Background: Electronic patient reported outcomes (ePROs) have become routine in cancer care; however, ePROs alone do not provide sufficient information to enable informed symptom management. Informed symptom management requires an awareness of patient context to reduce inappropriate or erroneous advice. In this project we asked: how can information be collected directly from patients to provide clinicians with detailed, contextually-informed, patient-specific, evidence-based recommendations to manage distressing symptoms, especially among patients with complex comorbidities. Methods: The literature states that text messages are the most effective way to engage patients in clinical data collection. We texted patients a link that led them to a Web-based questionnaire that asked them about their common cancer symptoms. Prototypes were tested with 9 cancer patients through structured interviews and think aloud sessions from which themes were identified. Feedback from these interviews was used to develop a patient data collection questionnaire that we iteratively refined through think aloud sessions with 9 cancer patients to achieve universal patient acceptance. We also engaged 28 oncology clinicians in semi-structured interviews to assess the clinical impact of the additional contextual information on the symptom recommendations they received. Results: Formative evaluation identified four themes: 1) make instructions brief, 2) use intuitive navigation buttons with labels, 3) focus on multiple-choice style questions, and 4) extract data from the medical record for patient verification instead of free text entry by patients (e.g., medications). Developers incorporated “more detailed” questions into the patient data collection questionnaire; additional questions were presented if the patient indicated moderate or greater severity of a given symptom. These detailed questions focused on characteristics of the symptoms (e.g. neuropathic or somatic pain), remedies a patient had already initiated for self treatment (e.g., laxatives for constipation), and comorbid conditions that could impact the safety of recommendations (e.g., fall risk). Clinicians indicated that the additional data collected from patients increased the value of the tailored recommendations for enhanced symptom management. Conclusions: Additional data collection from patients using standard text messaging enables clinical decision support algorithms to provide more individually tailored cancer symptom management recommendations. This study is limited in that the design enhancements have been tested with a small number of end-users in a laboratory setting. Acknowledgements: This project was 100% funded using Cancer Moonshot funding through Phase I and II SBIR contracts from the National Cancer Institute, Contract #75N91018C00022 and #75N91020C00019, respectively.

Scaffolding the human partner by contrastive guidance in an explanatory human-robot dialogue.

Explanation has been identified as an important capability for AI-based systems, but research on systematic strategies for achieving understanding in interaction with such systems is still sparse. Negation is a linguistic strategy that is often used in explanations. It creates a contrast space between the affirmed and the negated item that enriches explaining processes with additional contextual information. While negation in human speech has been shown to lead to higher processing costs and worse task performance in terms of recall or action execution when used in isolation, it can decrease processing costs when used in context. So far, it has not been considered as a guiding strategy for explanations in human-robot interaction. We conducted an empirical study to investigate the use of negation as a guiding strategy in explanatory human-robot dialogue, in which a virtual robot explains tasks and possible actions to a human explainee to solve them in terms of gestures on a touchscreen. Our results show that negation vs. affirmation 1) increases processing costs measured as reaction time and 2) increases several aspects of task performance. While there was no significant effect of negation on the number of initially correctly executed gestures, we found a significantly lower number of attempts-measured as breaks in the finger movement data before the correct gesture was carried out-when being instructed through a negation. We further found that the gestures significantly resembled the presented prototype gesture more following an instruction with a negation as opposed to an affirmation. Also, the participants rated the benefit of contrastive vs. affirmative explanations significantly higher. Repeating the instructions decreased the effects of negation, yielding similar processing costs and task performance measures for negation and affirmation after several iterations. We discuss our results with respect to possible effects of negation on linguistic processing of explanations and limitations of our study.

Evaluating ChatGPT responses in the context of a 53-year-old male with a femoral neck fracture: a qualitative analysis

PurposeThe integration of artificial intelligence (AI) tools, such as ChatGPT, in clinical medicine and medical education has gained significant attention due to their potential to support decision-making and improve patient care. However, there is a need to evaluate the benefits and limitations of these tools in specific clinical scenarios.MethodsThis study used a case study approach within the field of orthopaedic surgery. A clinical case report featuring a 53-year-old male with a femoral neck fracture was used as the basis for evaluation. ChatGPT, a large language model, was asked to respond to clinical questions related to the case. The responses generated by ChatGPT were evaluated qualitatively, considering their relevance, justification, and alignment with the responses of real clinicians. Alternative dialogue protocols were also employed to assess the impact of additional prompts and contextual information on ChatGPT responses.ResultsChatGPT generally provided clinically appropriate responses to the questions posed in the clinical case report. However, the level of justification and explanation varied across the generated responses. Occasionally, clinically inappropriate responses and inconsistencies were observed in the generated responses across different dialogue protocols and on separate days.ConclusionsThe findings of this study highlight both the potential and limitations of using ChatGPT in clinical practice. While ChatGPT demonstrated the ability to provide relevant clinical information, the lack of consistent justification and occasional clinically inappropriate responses raise concerns about its reliability. These results underscore the importance of careful consideration and validation when using AI tools in healthcare. Further research and clinician training are necessary to effectively integrate AI tools like ChatGPT, ensuring their safe and reliable use in clinical decision-making.

Francis Williams: Shedding light on the production, materials and techniques of the portrait of a Jamaican scholar

AbstractThe Victoria and Albert Museum holds an important portrait of the Jamaican scholar and writer Francis Williams (c.1692/97–1762), portrayed as a scholar in his study. It is believed to have been painted around 1745 by an unknown artist, but the circumstances of its production are unknown. A technical examination of the painting was performed using x‐radiography and infrared reflectography (IRR), macro x‐ray fluorescence scanning (XRF), digital microscopy, scanning electron microscopy with energy‐dispersive x‐ray spectroscopy (SEM–EDX) and reflectance imaging spectroscopy in the short‐wave infrared (SWIR). XRF, IRR and reflectance imaging spectroscopy in the SWIR revealed the distribution of inorganic pigments including lead white, earth pigments, Prussian blue, vermilion, orpiment (or pararealgar) and bone or ivory black. Pentimenti and a different sketched landscape were observed in the IRR images, highlighting changes in the final composition. Three‐dimensional (3D) digital microphotography provided additional historical and contextual information through the observation of book titles and details. High‐resolution digital imaging complemented analytical data. Results of the technical examination revealed the material composition and the development of the painting, contributing to shed new light on the production of the portrait, the history and significance of the portrait.

SMIN: Semi-Supervised Multi-Modal Interaction Network for Conversational Emotion Recognition

Conversational emotion recognition is a crucial research topic in human-computer interactions. Due to the heavy annotation cost and inevitable label ambiguity, collecting large amounts of labeled data is challenging and expensive, which restricts the performance of current fully-supervised methods in this domain. To address this problem, researchers attempt to distill knowledge from unlabeled data via semi-supervised learning. However, most of these semi-supervised methods ignore multimodal interactive information, although recent works have proven that such interactive information is essential for emotion recognition. To this end, we propose a novel framework to seamlessly integrate semi-supervised learning with multimodal interactions, called ‘`Semi-supervised Multi-modal Interaction Network (SMIN)’'. SMIN contains two well-designed semi-supervised modules, ‘`Intra-modal Interactive Module (IIM)’' and ‘`Cross-modal Interactive Module (CIM)’' to learn intra- and cross-modal interactions. These two modules leverage additional unlabeled data to extract emotion-salient representations. To capture additional contextual information, we utilize the hierarchical recurrent networks followed with the hybrid fusion strategy to integrate multimodal features. These multimodal features are further utilized for conversational emotion recognition. Experimental results on four benchmark datasets (i.e., IEMOCAP, MELD, CMU-MOSI and CMU-MOSEI) demonstrate that SMIN succeeds over existing state-of-the-art strategies on emotion recognition.

Estimating Systemic Cognitive States from a Mixture of Physiological and Brain Signals.

As human-machine teams are being considered for a variety of mixed-initiative tasks, detecting and being responsive to human cognitive states, in particular systematic cognitive states, is among the most critical capabilities for artificial systems to ensure smooth interactions with humans and high overall team performance. Various human physiological parameters, such as heart rate, respiration rate, blood pressure, and skin conductance, as well as brain activity inferred from functional near-infrared spectroscopy or electroencephalogram, have been linked to different systemic cognitive states, such as workload, distraction, or mind-wandering among others. Whether these multimodal signals are indeed sufficient to isolate such cognitive states across individuals performing tasks or whether additional contextual information (e.g., about the task state or the task environment) is required for making appropriate inferences remains an important openproblem. In this paper, we introduce an experimental and machine learning framework for investigating these questions and focus specifically on using physiological and neurophysiological measurements to learn classifiers associated with systemic cognitive states like cognitive load, distraction, sense of urgency, mind wandering, and interference. Specifically, we describe a multitasking interactive experimental setting used to obtain a comprehensive multimodal data set which provided the foundation for a first evaluation of various standard state-of-the-art machine learning techniques with respect to their effectiveness in inferring systemic cognitive states. While the classification success of these standard methods based on just the physiological and neurophysiological signals across subjects was modest, which is to be expected given the complexity of the classification problem and the possibility that higher accuracy rates might not in general be achievable, the results nevertheless can serve as a baseline for evaluating future efforts to improve classification, especially methods that take contextual aspects such as task and environmental states into account.

Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features.

Compared with other point clouds, the airborne LiDAR point cloud has its own characteristics. The deep learning network PointNet++ ignores the inherent properties of airborne LiDAR point, and the classification precision is low. Therefore, we propose a framework based on the PointNet++ network. In this work, we proposed an interpolation method that uses adaptive elevation weight to make full use of the objects in the airborne LiDAR point, which exhibits discrepancies in elevation distributions. The class-balanced loss function is used for the uneven density distribution of point cloud data. Moreover, the relationship between a point and its neighbours is captured, densely connecting point pairs in multiscale regions and adding centroid features to learn contextual information. Experiments are conducted on the Vaihingen 3D semantic labelling benchmark dataset and GML(B) benchmark dataset. The experiments show that the proposed method, which has additional contextual information and makes full use of the airborne LiDAR point cloud properties to support classification, achieves high accuracy and can be widely used in airborne LiDAR point classification.