Low-level Tasks Research Articles

우리나라와 미국 교과서의 사각형의 성질 과제 비교

In order to derive implications for the reasoning tasks presented in Korean textbooks, this study classified tasks of the proposition of quadrilateral unit in Korean and U.S. textbooks into type of proof-related reasoning, analyzed them according to the level of reasoning and argument competency demands. In addition, detailed characteristics according to each level were examined for tasks of the types of DA, IC and MC that accounted for the majority. As a result of the analysis, low-level tasks were presented at a high rate in both countries, but the proportion of high-level tasks was higher in U.S. textbooks. Additionally, opportunities to develop reasoning and argument competency were provided at a limited level for each type of reasoning. This tendency could be clearly confirmed based on the detailed characteristics of reasoning tasks related to the proposition of quadrilateral unit in Korea, examined by the type of reasoning. Therefore Korean textbooks need to provide opportunities to learn high-level reasoning, to present tasks at various levels according to each type of reasoning furthermore, and to reconsider how to develop and transform tasks of various levels for each reasoning type in terms of element and the chain of inference.

A reflectance re-weighted Retinex model for non-uniform and low-light image enhancement

Image enhancement is a fundamental low-level task of significant importance that can directly affect high-level image processing tasks. Although various methods have been proposed to enhance images, the effectiveness of current methods deteriorates significantly under non-uniform lighting. Since the brightness may vary dramatically in different regions of real-world photos, current methods hardly achieve a good balance between enhancing low-light regions and retaining normal-light regions in the same image. Consequently, either the low-light regions are under-enhanced or the normal-light regions are over-enhanced, while at the same time, color distortion and artifacts are frequently found. To overcome this shortcoming, we propose a robust Retinex-based model with reflectance map re-weighting that can improve the brightness level of the low-light image and re-balance the brightness concurrently. We introduce an alternating scheme to solve our proposed model, in which the illumination map, reflectance map, and weighting map are updated iteratively. By utilizing the regularization terms, the noise is well-suppressed during the process. An initialization scheme for the weighting map is also proposed to make our model adaptable to a wide range of light conditions. To the best of our knowledge, we are the first to propose a variational model with an explicitly constructed re-weighting prior and the associated weighing map concept for the reflectance map. It can estimate the reflectance map, suppress noise, and re-balance the brightness simultaneously. A series of experimental results on a variety of popular datasets demonstrate the efficacy of our method and its superiority in enhancing real low-light images when compared to other state-of-the-art methods.

Increasing the efficiency of cargo handling at a modern warehouse terminal

Problem. The task of increasing the efficiency of cargo handling at a modern warehouse terminal is considered. The need to introduce intelligent cargo handling systems has increased due to the increased demand for supplies and the reduction of personnel in the field of logistics. When analyzing the current state of terminal transportation, it was found that the volume of transportation exceeds the capacity of the terminals. Goal. The goal is to choose a set of technical means of identification and means of cargo transportation for the management of the terminal, which will increase the efficiency and speed of cargo handling operations in the warehouse taking into account the specified criteria and restrictions. Methodology. The task of choosing a identification system is complicated by the ambiguity of various system parameters and characteristics. Their inconsistency complicates the design process. To solve this problem, the principle of system decomposition is used, in which the solution of lower-level tasks, which have their own criteria and restrictions, leads to the solution of the general design problem taking into account these limitations. The task of choosing technical means belongs to the class of multi-criteria and can be solved by methods of multi-criteria optimization of this type of objects. Results. The technology of automated design of the warehouse terminal has been developed. Models for selecting components of the logistic terminal control system have been developed. An example of the selection of the element base of the identification and transportation system according to the specified criteria and restrictions is given. Originality. The originality lies in the fact that the using intelligent components of information processing systems allow to increase warehouse terminal productivity. Practical value. Using the technology of automated design of modern warehouse terminals, a number of issues related to the accuracy, quality and speed of decision-making during cargo handling are solved.

APUNet: Attention-guided upsampling network for sparse and non-uniform point cloud

Point cloud upsampling is a basic low-level task, that is important for improving the quality of a point cloud. However, existing point cloud upsampling methods perform poorly on sparse and non-uniform point clouds, due to that they fail to fully model the relationship between points. To address this issue, in this paper, we propose an attention-guided network called APUNet to exploit the correlation between points, which can perform unsampling for sparse and non-uniform point cloud. In particular, we first propose a feature extraction unit, DisTransformer, which can effectively model the relationship between points by introducing a distance prior to the attention mechanism. We also design a point cloud feature extraction network based on DisTransformer. By computing the correlation between patches and the correlation between points, we fuse the global and local features to better model the correlation of the whole object. Furthermore, we propose a feature prediction module based on attention mechanisms that avoids generating clustered points by transforming the point cloud expansion task into a point cloud prediction task. Qualitative and quantitative experiments reveal the superiority of our method compared to the current state-of-the-art methods. Compared with other point cloud upsampling methods, APUNet can much better upsample non-uniform and extremely sparse point clouds.

Engineering Rehabilitation: Blending Two Tool-supported Approaches to Close the Loop from Tasks-based Rehabilitation to Exercises and Back Again

Post-stroke or post-brain injuries rehabilitation is a long-term process defined by therapists and tuned to the specific damages and their consequences for each patient. This process requires the definition of well-defined multiple exercises to be performed multiple times by each patient over a long period of time. One of the key findings in the rehabilitation domain is that exercises should be tasks and goals oriented to increase functional independence, enhance development and prevent disability [24]. Patients performing the exercises must be carefully monitored to identify progress, possible regression and prevent damages due to the inadequate performance of the exercises. The SIVIRE tool [20] provides interactive graphical feedback to patients about the performance of their exercises and deviations from nominal, planed practice but fails at providing high-level descriptions of exercises and at connecting them to high-level rehabilitation goals (e.g. gain autonomy in cleaning a room). The HAMSTERS-XLE tool [16] provides a tuneable editor and a simulator to describe goals and task models including low-level tasks covering perception of the various senses, cognition and motoric actions. This paper presents the integration of these two tools and the benefits it brings both to the patients and to the therapists. The resulting tool and its engineering are presented in detail highlighting some generic integration mechanisms. On a case study, we show how exercises can be defined in HAMSTERS-XLE, transferred to SIVRE for fine tuning, monitored by SIVRE during the multiple practices of the patient and transferred back again to HAMSTERS-XLE to monitor progress, identify issues with the exercises and provide therapists with goal and task-based data about patients' evolutions

Conscientious, competent and caring: producing the junior doctor of the future.

This article is based on the Association for the Study of Medical Education Gold Medal Plenary for 2022, given by the first author. It outlines different ways in which medical training can be approached, based on his career and his work with colleagues. Among the attributes that it would be desirable to promote in future doctors are conscientiousness, competence and care for patients as individuals. This article explores each of these in separate sections. The first demonstrates that the trait of conscientiousness can be observed in first and second year medical students by their compliance in routine low level tasks such as attendance and submission of required work on time. A 'conscientiousness index' calculated on this basis is a statistically significant predictor of later events such as performance in exams, the prescribing safety assessment, and the UK situational judgement test in subsequent years, and also in postgraduate assessments such as Royal college exams and the annual reviews of competence progression. The second proposes that competence in tasks undertaken by junior doctors is better achieved by teaching on medical imaging, clinical skills and living anatomy than by cadaveric dissection. The final section argues that the incorporation of arts and humanities teaching into medical education is likely to lead to better understanding of the patient perspective in later practice.

Refrigerant selection from an economic and TEWI analysis of cascade refrigeration systems in Europe based on annual weather data

Due to environmental concerns and increasingly stringent regulations, refrigerants with low global warming potential must be used in cascade refrigeration systems. However, identifying the most suitable combination of refrigerants is still a major challenge. Therefore, a methodology for selecting refrigerant combinations for cascade refrigeration systems dedicated to freezing applications is presented. A bilevel optimization procedure approach based on a thermodynamic 0D-steady state model and weather data at different locations in Europe (i.e. France, Germany and Spain) has been developed. The system is optimized in terms of the coefficient of performance on an hourly basis as the lower level task and the total annual cost as the upper level task. The results are analyzed with respect to the annual cost and the corresponding Total Equivalent Warming Impact (TEWI). In total, 36 different low GWP refrigerant pairs were studied for a cascade refrigeration system with an imposed cooling load of 100kW. The results of the analysis show that dimethyl ether and R161 have the best performance for the high temperature circuit. However, close performances were obtained with R717 and R152a. For the low temperature circuit, similar results were observed for R41, R170 and R744. For the R161/R744 pair, the optimal annual cost and corresponding TEWI are 141 285€year−1 and 3001t, 108 858€year−1 and 2459t, 105 179€year−1 and 533t for Berlin, Madrid and Paris, respectively. Furthermore, the study shows that the optimal refrigerant selection of the investigated refrigerants is robust for the cooled space temperature and the location of the cascade refrigeration system, as no significant change of the TEWI and the total annual cost ranking of the individual refrigerants is observed.

PT-FlowNet: Scene Flow Estimation on Point Clouds With Point Transformer

As a low-level task of 3D perception, scene flow is a fundamental representation of dynamic scenes and provides non-rigid motion descriptions for the objects in the 3D environment, which can strongly support many upper-level applications. Inspired by the revolutionary success of deep learning, many attention-based neural networks have recently been proposed to estimate scene flow from consecutive point clouds. However, extracting effective features and estimating accurate point motions for irregular and occluded point clouds remains a challenging task. In this paper, we propose PT-FlowNet, the first end-to-end scene flow estimation network embedding the point transformer (PT) into all functional stages of the task. In particular, we design novel PT-based modules for point feature extraction, iterative flow update, and flow refinement stage to encourage effective point-level feature aggregation. Experimental results on FlyingThings3D and KITTI datasets show that our PT-FlowNet achieves state-of-the-art performance. Trained on synthetic data only, our PT-FlowNet can generalize to real-world scans and outperforms the existing methods by at least 36.2% for the EPE3D metric on the KITTI dataset. Code and models can be accessed at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/FuJingyun/PT-FlowNet</uri> .

Computational Offloading for MEC Networks with Energy Harvesting: A Hierarchical Multi-Agent Reinforcement Learning Approach

Multi-access edge computing (MEC) is a novel computing paradigm that leverages nearby MEC servers to augment the computational capabilities of users with limited computational resources. In this paper, we investigate the computational offloading problem in multi-user multi-server MEC systems with energy harvesting, aiming to minimize both system latency and energy consumption by optimizing task offload location selection and task offload ratio.We propose a hierarchical computational offloading strategy based on multi-agent reinforcement learning (MARL). The proposed strategy decomposes the computational offloading problem into two sub-problems: a high-level task offloading location selection problem and a low-level task offloading ratio problem. The complexity of the problem is reduced by decoupling. To address these sub-problems, we propose a computational offloading framework based on multi-agent proximal policy optimization (MAPPO), where each agent generates actions based on its observed private state to avoid the problem of action space explosion due to the increasing number of user devices. Simulation results show that the proposed HDMAPPO strategy outperforms other baseline algorithms in terms of average task latency, energy consumption, and discard rate.

Deep Optical Coding Design in Computational Imaging: A data-driven framework

Computational optical imaging (COI) systems leverage optical coding elements (CEs) in their setups to encode a high-dimensional scene in a single or in multiple snapshots and decode it by using computational algorithms. The performance of COI systems highly depends on the design of its main components: the CE pattern and the computational method used to perform a given task. Conventional approaches rely on random patterns or analytical designs to set distribution of the CE. However, the available data and algorithm capabilities of deep neural networks (DNNs) have opened a new horizon in CE data-driven designs that jointly consider the optical and computational decoders. Specifically, by modeling the COI measurements through a fully differentiable image-formation model that considers the physics-based propagation of light and its interaction with the CEs, the parameters that define the CE and the computational decoder can be optimized in an end-to-end (E2E) manner. Moreover, by optimizing just CEs in the same framework, inference tasks can be performed from pure optics. This work surveys the recent advances in CE data-driven design and provides guidelines on how to parameterize different optical elements to include them in the E2E framework. As the E2E framework can handle different inference applications by changing the loss function and the DNN, we present low-level tasks such as spectral imaging reconstruction or high-level tasks such as pose estimation with privacy preservation enhanced by using optimal task-based optical architectures. Finally, we illustrate classification and 3D object-recognition applications performed at the speed of the light using all-optics DNNs.

WAMF-FPI: A Weight-Adaptive Multi-Feature Fusion Network for UAV Localization

UAV localization in denial environments is a hot research topic in the field of cross-view geo-localization. The previous methods tried to find the corresponding position directly in the satellite image through the UAV image, but they lacked the consideration of spatial information and multi-scale information. Based on the method of finding points with an image, we propose a novel architecture—a Weight-Adaptive Multi-Feature fusion network for UAV localization (WAMF-FPI). We treat this positioning as a low-level task and achieve more accurate localization by restoring the feature map to the resolution of the original satellite image. Then, in order to enhance the ability of the model to solve multi-scale problems, we propose a Weight-Adaptive Multi-Feature fusion module (WAMF), which introduces a weighting mechanism to fuse different features. Finally, since all positive samples are treated in the same way in the existing methods, which is very disadvantageous for accurate localization tasks, we introduce Hanning loss to allow the model to pay more attention to the central area of the target. Our model achieves competitive results on the UL14 dataset. When using RDS as the evaluation metric, the performance of the model improves from 57.22 to 65.33 compared to Finding Point with Image (FPI). In addition, we calculate the actual distance errors (meters) to evaluate the model performance, and the localization accuracy at the 20 m level improves from 57.67% to 69.73%, showing the powerful performance of the model. Although the model shows better performance, much remains to be done before it can be applied.

An Accurate Deep Learning–Based System for Automatic Pill Identification: Model Development and Validation

Medication errors account for a large proportion of all medical errors. In most homes, patients take a variety of medications for a long period. However, medication errors frequently occur because patients often throw away the containers of their medications. We proposed a deep learning-based system for reducing medication errors by accurately identifying prescription pills. Given the pill images, our system located the pills in the respective pill databases in South Korea and the United States. We organized the system into a pill recognition step and pill retrieval step, and we applied deep learning models to train not only images of the pill but also imprinted characters. In the pill recognition step, there are 3 modules that recognize the 3 features of pills and their imprints separately and correct the recognized imprint to fit the actual data. We adopted image classification and text detection models for the feature and imprint recognition modules, respectively. In the imprint correction module, we introduced a language model for the first time in the pill identification system and proposed a novel coordinate encoding technique for effective correction in the language model. We identified pills using similarity scores of pill characteristics with those in the database. We collected the open pill database from South Korea and the United States in May 2022. We used a total of 24,404 pill images in our experiments. The experimental results show that the predicted top-1 candidates achieve accuracy levels of 85.6% (South Korea) and 74.5% (United States) for the types of pills not trained on 2 different databases (South Korea and the United States). Furthermore, the predicted top-1 candidate accuracy of our system was 78% with consumer-granted images, which was achieved by training only 1 image per pill. The results demonstrate that our system could identify and retrieve new pills without additional model updates. Finally, we confirmed through an ablation study that the language model that we emphasized significantly improves the pill identification ability of the system. Our study proposes the possibility of reducing medical errors by showing that the introduction of artificial intelligence can identify numerous pills with high precision in real time. Our study suggests that the proposed system can reduce patients' misuse of medications and help medical staff focus on higher-level tasks by simplifying time-consuming lower-level tasks such as pill identification.

A Survey of Perception-Based Visualization Studies by Task

Knowledge of human perception has long been incorporated into visualizations to enhance their quality and effectiveness. The last decade, in particular, has shown an increase in perception-based visualization research studies. With all of this recent progress, the visualization community lacks a comprehensive guide to contextualize their results. In this report, we provide a systematic and comprehensive review of research studies on perception related to visualization. This survey reviews perception-focused visualization studies since 1980 and summarizes their research developments focusing on low-level tasks, further breaking techniques down by visual encoding and visualization type. In particular, we focus on how perception is used to evaluate the effectiveness of visualizations, to help readers understand and apply the principles of perception of their visualization designs through a task-optimized approach. We concluded our report with a summary of the weaknesses and open research questions in the area.

Ontology-based surgical workflow recognition and prediction

BackgroundSurgical context-aware systems can adapt to the current situation in the operating room and thus provide computer-aided assistance functionalities and intraoperative decision-support. To interact with the surgical team perceptively and assist the surgical process, the system needs to monitor the intraoperative activities, understand the current situation in the operating room at any time, and anticipate the following possible situations. MethodsA structured representation of surgical process knowledge is a prerequisite for any applications in the intelligent operating room. For this purpose, a surgical process ontology, which is formally based on standard medical terminology (SNOMED CT) and an upper-level ontology (GFO), was developed and instantiated for a neurosurgical use case. A new ontology-based surgical workflow recognition and a novel prediction method are presented utilizing ontological reasoning, abstraction, and explication. This way, a surgical situation representation with combined phase, high-level task, and low-level task recognition and prediction was realized based on the currently used instrument as the only input information. ResultsThe ontology-based approach performed efficiently, and decent accuracy was achieved for situation recognition and prediction. Especially during situation recognition, the missing sensor information were reasoned based on the situation representation provided by the process ontology, which resulted in improved recognition results compared to the state-of-the-art. ConclusionsIn this work, a reference ontology was developed, which provides workflow support and a knowledge base for further applications in the intelligent operating room, for instance, context-aware medical device orchestration, (semi-) automatic documentation, and surgical simulation, education, and training.

A generic neural factor linking resting-state neural dynamics and the brain's response to unexpectedness in multilevel cognition.

The brain's response to change is fundamental to learning and adaptation; this implies the presence of a universal neural mechanism under various contexts. We hypothesized that this mechanism manifests in neural activity patterns across low and high levels of cognition during task processing as well as in resting-state neural dynamics, because both these elements are different facets of the same dynamical system. We tested our hypothesis by (i) characterizing (a) the neural response to changes in low-level continuous information stream and unexpectedness at different cognitive levels and (b) the spontaneous neural dynamics in resting state, and (ii) examining the associations among the dynamics according to cross-individual variability (n= 200). Our results showed that the brain's response magnitude was monotonically correlated with the magnitude of information fluctuation in a low-level task, forming a simple psychophysical function; moreover, this effect was found to be associated with the brain's response to unexpectedness in high-level cognitive tasks (including language processing). These coherent multilevel neural effects in task processing were also shown to be strongly associated with resting-state neural dynamics characterized by the waxing and waning of Alpha oscillation. Taken together, our results revealed large-scale consistency between the neural dynamic system and multilevel cognition.

BaMBNet: A Blur-Aware Multi-Branch Network for Dual-Pixel Defocus Deblurring

Reducing the defocus blur that arises from the finite aperture size and short exposure time is an essential problem in computational photography. It is very challenging because the blur kernel is spatially varying and difficult to estimate by traditional methods. Due to its great breakthrough in low-level tasks, convolutional neural networks (CNNs) have been introduced to the defocus deblurring problem and achieved significant progress. However, previous methods apply the same learned kernel for different regions of the defocus blurred images, thus it is difficult to handle nonuniform blurred images. To this end, this study designs a novel blur-aware multi-branch network (Ba-MBNet), in which different regions are treated differentially. In particular, we estimate the blur amounts of different regions by the internal geometric constraint of the dual-pixel (DP) data, which measures the defocus disparity between the left and right views. Based on the assumption that different image regions with different blur amounts have different deblurring difficulties, we leverage different networks with different capacities to treat different image regions. Moreover, we introduce a meta-learning defocus mask generation algorithm to assign each pixel to a proper branch. In this way, we can expect to maintain the information of the clear regions well while recovering the missing details of the blurred regions. Both quantitative and qualitative experiments demonstrate that our BaMBNet outperforms the state-of-the-art (SOTA) methods. For the dual-pixel defocus deblurring (DPD)-blur dataset, the proposed BaMBNet achieves 1.20 dB gain over the previous SOTA method in term of peak signal-to-noise ratio (PSNR) and reduces learnable parameters by 85%. The details of the code and dataset are available at https://github.com/junjun-jiang/BaMBNet.

Joint Learning of Multi-Level Tasks for Diabetic Retinopathy Grading on Low-Resolution Fundus Images.

Diabetic retinopathy (DR) is a leading cause of permanent blindness among the working-age people. Automatic DR grading can help ophthalmologists make timely treatment for patients. However, the existing grading methods are usually trained with high resolution (HR) fundus images, such that the grading performance decreases a lot given low resolution (LR) images, which are common in clinic. In this paper, we mainly focus on DR grading with LR fundus images. According to our analysis on the DR task, we find that: 1) image super-resolution (ISR) can boost the performance of both DR grading and lesion segmentation; 2) the lesion segmentation regions of fundus images are highly consistent with pathological regions for DR grading. Based on our findings, we propose a convolutional neural network (CNN)-based method for joint learning of multi-level tasks for DR grading, called DeepMT-DR, which can simultaneously handle the low-level task of ISR, the mid-level task of lesion segmentation and the high-level task of disease severity classification on LR fundus images. Moreover, a novel task-aware loss is developed to encourage ISR to focus on the pathological regions for its subsequent tasks: lesion segmentation and DR grading. Extensive experimental results show that our DeepMT-DR method significantly outperforms other state-of-the-art methods for DR grading over three datasets. In addition, our method achieves comparable performance in two auxiliary tasks of ISR and lesion segmentation.

Problem-Based Learning Impacts Students’ Reported Learning and Confidence in an Undergraduate Biomedical Engineering Course

Recent advances in teaching, many of which incorporate elements of active learning, seek to provide students with learning experiences indicative of real-world problem solving. Problem-based learning (PBL) is one form of active learning that challenges students to address open-ended problems. In this work, we evaluate the efficacy of PBL in achieving the various levels of Bloom’s Taxonomy, compared to the traditional teaching methods of lecture, in-class problems, and homework. In this two-year study of undergraduates at a mid-sized research university, students report their perceived rating of various teaching methods in mastering the educational goals on each level of Bloom’s Taxonomy, from which a cumulative linked mixed model was formed. Students also evaluated their preparedness and increases in skill and confidence for a range of specific tasks associated with completing a PBL project. PBL was the only teaching method to preferentially activate high levels of Bloom’s Taxonomy. Students also reported increases in their skills and confidence (p < 0.01), with more time spent on high-level tasks, compared to low-level tasks. Qualitative survey responses indicate a plurality of students found PBL engaging and rewarding, with additional benefits to their development of professional skills. Though PBL is not comprehensively better at addressing all levels of Bloom’s Taxonomy compared to other teaching methods, this work has shown it is far superior at addressing the highest Bloom’s Taxonomy levels of Evaluate and Create. Time spent in PBL improves students’ self-efficacy in high-level tasks, preparing them for difficult and ill-defined tasks they may expect to see in future professional and academic environments.

Improving Performance on Low-Level Audit Tasks: The Interactive Effect of Regulatory Fit and Professional Identity

ABSTRACTAuditing standards vary in their degree of prescriptive language—for example, stating that auditors “could” versus “should” do certain procedures. We posit that more prescriptive language primes an implemental mindset, thereby creating a feeling of regulatory fit with objective verification tasks and improving auditors' performance on these tasks. In an experiment with audit students, we find that participants who apply a more (versus less) prescriptive auditing standard perform better on a subsequent, unrelated ticking-and-tying task, and this effect is larger for participants who identify less with the audit profession. Theory-consistent evidence indicates that the interaction of regulatory fit and professional identity improves performance via increased motivation. Our study provides evidence that features of the audit environment prime mindsets, that these primed mindsets can affect performance on low-level tasks, and that the effect of regulatory fit for low-level tasks is particularly important for those who identify less with the audit profession.

Searching for Robustness Intervals in Evolutionary Robust Optimization

In many real-world optimization applications, a goal solution (i.e., scenario) is often provided by a user according to his/her experience. Due to the presence of a wide range of uncertainties, one may be interested in identifying the robustness interval of the solution, i.e., the range of the decision variables in which the solution remains robust. This article investigates how to find the robustness intervals of the goal solution in evolutionary robust optimization and formulates this as a bilevel optimization problem. Then, a novel algorithm framework is proposed to solve the bilevel problem: an efficient heuristic-based approach is developed to optimize the upper level task, while a global optimizer is utilized to tackle the lower level task. The proposed heuristic-based approach contains four key components: 1) peak detection; 2) peak allocation; 3) calculation of the next perturbation value; and 4) robustness interval fine-tuning, aiming to enhance the efficiency of searching for the target intervals. Finally, three types of artificial test problems and a practical problem are provided to verify the effectiveness of the proposed algorithm framework. The results show that all the robustness intervals can be successfully found when the goal solution is given by means of the proposed algorithm framework.