Real-world Tasks Research Articles

The pivotal role of clinical tutorial teaching in knowledge construction.

Students' new knowledge is gradually built up in the context of the task for which it is required and consolidated by applying it to clinical cases. As students see more and more clinical cases the knowledge emerges from an associative mesh of different levels of understanding. During tutorial clinical teaching, residents should be gradually exposed to an increasing range of real-world learning tasks and increasing levels of complexity. This exposure allows them to gradually develop shortcuts in the retrieval of their knowledge. This commentary provides a rationale for the construction of knowledge and the pivotal role that clinical tutorial teaching plays in this task.

Spatiotemporal implicit neural representation as a generalized traffic data learner

Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. Existing methods aim to reconstruct STTD using low-dimensional models. However, they are limited to data-specific dimensions or source-dependent patterns, restricting them from unifying representations. Here, we present a novel paradigm to address the STTD learning problem by parameterizing STTD as an implicit neural representation. To discern the underlying dynamics in low-dimensional regimes, coordinate-based neural networks that can encode high-frequency structures are employed to directly map coordinates to traffic variables. To unravel the entangled spatial–temporal interactions, the variability is decomposed into separate processes. We further enable modeling in irregular spaces such as sensor graphs using spectral embedding. Through continuous representations, our approach enables the modeling of a variety of STTD with a unified input, thereby serving as a generalized learner of the underlying traffic dynamics. It is also shown that it can learn implicit low-rank priors and smoothness regularization from the data, making it versatile for learning different dominating data patterns. We validate its effectiveness through extensive experiments in real-world scenarios, showcasing applications from corridor to network scales. Empirical results not only indicate that our model has significant superiority over conventional low-rank models, but also highlight that the versatility of the approach extends to different data domains, output resolutions, and network topologies. Comprehensive model analyses provide further insight into the inductive bias of STTD. We anticipate that this pioneering modeling perspective could lay the foundation for universal representation of STTD in various real-world tasks. PyTorch implementations of this project is publicly available at:https://github.com/tongnie/traffic_dynamics.

Why authenticity matters: a qualitative investigation of students’ perceptions of personal values in first-year assessments

ABSTRACT Authentic assessments in higher education typically imply the replication of real-world tasks. Psychological authenticity is the perceived alignment between an individual’s internal reference sources (i.e. personal values and beliefs) and their actions. Applying psychological authenticity logic to assessment tasks, we investigated students’ perceptions of scaffolded first-year assessment tasks on their health behaviour. In particular, we explored the meaning and value students associated with these tasks. One hundred students (86 female) completed an online open-text survey. Following our thematic analysis of the data, we constructed two higher-order themes. First, ‘the assessments were the catalyst for enabling self-reflection’ exemplified the opportunity students were afforded to reflect upon their current health behaviour. Second, ‘most changed for the better, but some stayed the same’ captured the dichotomy of student perceptions in completing the assessment tasks. Collectively, our findings offer new insights into authenticity in higher education assessment practices.

Practical Verification of Smart Contracts using Memory Splitting

SMT-based verification of low-level code requires modeling and reasoning about memory operations. Prior work has shown that optimizing memory representations is beneficial for scaling verification—pointer analysis, for example can be used to split memory into disjoint regions leading to faster SMT solving. However, these techniques are mostly designed for C and C++ programs with explicit operations for memory allocation which are not present in all languages. For instance, on the Ethereum virtual machine, memory is simply a monolithic array of bytes which can be freely accessed by Ethereum bytecode, and there is no allocation primitive. In this paper, we present a memory splitting transformation guided by a conservative memory analysis for Ethereum bytecode generated by the Solidity compiler. The analysis consists of two phases: recovering memory allocation and memory regions, followed by a pointer analysis. The goal of the analysis is to enable memory splitting which in turn speeds up verification. We implemented both the analysis and the memory splitting transformation as part of a verification tool, CertoraProver, and show that the transformation speeds up SMT solving by up to 120x and additionally mitigates 16 timeouts when used on 229 real-world smart contract verification tasks.

Investigating the effect of template head models on Event-Related Potential source localization: a simulation and real-data study.

Event-Related Potentials (ERPs) are valuable for studying brain activity with millisecond-level temporal resolution. While the temporal resolution of this technique is excellent, the spatial resolution is limited. Source localization aims to identify the brain regions generating the EEG data, thus increasing the spatial resolution, but its accuracy depends heavily on the head model used. This study compares the performance of subject-specific and template-based head models in both simulated and real-world ERP localization tasks. Simulated data mimicking realistic ERPs was created to evaluate the impact of head model choice systematically, after which subject-specific and template-based head models were used for the reconstruction of the data. The different modeling approaches were also applied to a face recognition dataset. The results indicate that the template models capture the simulated activity less accurately, producing more spurious sources and identifying less true sources correctly. Furthermore, the results show that while creating more accurate and detailed head models is beneficial for the localization accuracy when using subject-specific head models, this is less the case for template head models. The main N170 source of the face recognition dataset was correctly localized to the fusiform gyrus, a known face processing area, using the subject-specific models. Apart from the fusiform gyrus, the template models also reconstructed several other sources, illustrating the localization inaccuracies. While template models allow researchers to investigate the neural generators of ERP components when no subject-specific MRIs are available, it could lead to misinterpretations. Therefore, it is important to consider a priori knowledge and hypotheses when interpreting results obtained with template head models, acknowledging potential localization errors.

Neuroergonomic Attention Assessment in Safety-Critical Tasks: EEG Indices and Subjective Metrics Validation in a Novel Task-Embedded Reaction Time Paradigm.

Background/Objectives: This study addresses the gap in methodological guidelines for neuroergonomic attention assessment in safety-critical tasks, focusing on validating EEG indices, including the engagement index (EI) and beta/alpha ratio, alongside subjective ratings. Methods: A novel task-embedded reaction time paradigm was developed to evaluate the sensitivity of these metrics to dynamic attentional demands in a more naturalistic multitasking context. By manipulating attention levels through varying secondary tasks in the NASA MATB-II task while maintaining a consistent primary reaction-time task, this study successfully demonstrated the effectiveness of the paradigm. Results: Results indicate that both the beta/alpha ratio and EI are sensitive to changes in attentional demands, with beta/alpha being more responsive to dynamic variations in attention, and EI reflecting more the overall effort required to sustain performance, especially in conditions where maintaining attention is challenging. Conclusions: The potential for predicting the attention lapses through integration of performance metrics, EEG measures, and subjective assessments was demonstrated, providing a more nuanced understanding of dynamic fluctuations of attention in multitasking scenarios, mimicking those in real-world safety-critical tasks. These findings provide a foundation for advancing methods to monitor attention fluctuations accurately and mitigate risks in critical scenarios, such as train-driving or automated vehicle operation, where maintaining a high attention level is crucial.

VR Simulation: Advancing Practical Skills in Computer Science Education

This study presents the successful integration of Virtual Reality (VR) tools as an element in the computer science curriculum at the German University of Technology, Oman. The research study investigates the use of MyScore, a VR application developed by RWTH Aachen University - Teaching & Research Field Engineering Hydrology as an environment for computer hardware assembly and troubleshooting exercises. The VR simulation utilized in this study acts as a gamified environment, incorporating elements like scorekeeping and interactive challenges to enhance practical learning in computer science, akin to game-based strategies that engage and motivate students. Over some weeks, the project involved seven students and one tutor in immersive learning sessions to develop applied skills in computer hardware assembly with VR technology over conventional teaching methods. Structured surveys and direct observations were used for data collection through students' interactions with the VR sessions. We also evaluated the student's learning experiences as well as the usability of technology. The results showed that the user-friendliness of the VR interface and its ability to accurately simulate real-world tasks associated with computer assembly received both positive and negative reactions. While some students praised the technology for being pretty cutting-edge, some criticized it as unrealistic or non-interactive. We also received complaints that ranged from actually moving around in the virtual space to navigating only through teleportation spark points. Specifically, two students got motion sickness, which is a well-known obstacle associated with VR environments, and consequently left the sessions prematurely. The feedback of the instructor pointed out that setting up the VR equipment is straightforward and described some potential methods. Still, a call for more reliability in simulations and better interfaces began to surface as nevertheless less controversial agenda items. However, the instructor saw how VR has the potential to revolutionize educational practices. Providing interactive views between the VR device and students that can act as new learning methods. The present study extends the discussion on educational technology by providing empirical evidence of the benefits and challenges experienced in deploying VR for technical education implementation. These findings thus support the continued development and validation of VR technologies in pursuit of improved commitment, cost-effectiveness, immersion, and environment quality that may maximize learning outcomes in future educational applications.

Reinforcement Learning with Decoupled State Representation for Robot Manipulations

Deep reinforcement learning has significantly advanced robot manipulations by providing an alternative solution for designing control strategies using raw images as direct inputs. While images offer additional environmental information, the end-to-end policy training manner (from image to action) requires simultaneous representation and task learning by the agent. This often necessitates a substantial number of interaction samples to achieve satisfactory policy performance. Previous works has attempted to address this challenge by learning a visual representation model that encodes the entire image into a low-dimensional vector before the policy training. However, since this vector contains both robot and object information, it inevitably introduces coupling within the state, which can mislead the policy training process. In this study, a novel method called Reinforcement Learning with Decoupled State Representation is proposed to effectively decouple robot and object information within the state representation. Experimental results demonstrate that the proposed method exhibits faster learning speed and achieves superior performance compared to previous methods across various robot manipulation tasks. Moreover, with only 3096 offline images, the proposed method successfully applies to real-world robot pushing tasks, which demonstrates its high practicability.

DESIGNING AND IMPLEMENTING APPLIED BACHELOR'S PROGRAM: A COMPREHENSIVE DEVELOPMENT MODEL

Modern education faces the challenge of integrating theoretical knowledge with practical skills, which is particularly crucial for the training of mid-level professionals. Practice-oriented educational programs shorten the adaptation period for graduates and enhance their competitiveness in the labor market. Special attention is given to applied bachelor's programs that combine theory and practice, fostering rapid professional development of graduates. The European higher education system offers short cycles leading to a bachelor's degree. The practical focus of these programs is ensured through partnerships between educational institutions and industry organizations, enabling students to develop the professional skills required by employers. This makes applied bachelor's programs key elements of educational reforms in the EU. In Kazakhstan, applied bachelor's programs have not yet gained widespread popularity due to a lack of regulatory support, but successful pilot projects demonstrate the potential of this direction. These programs integrate theoretical and practical training, approaching education with consideration of real-world functional tasks. The need to adapt educational programs to meet the current demands of the labor market is extremely important for preparing qualified personnel. This underscores the importance of continually improving educational initiatives to develop programs that successfully combine theory with practice and meet the needs of a dynamic economic environment.

Generative language models on nucleotide sequences of human genes.

Language models, especially transformer-based ones, have achieved colossal success in natural language processing. To be precise, studies like BERT for natural language understanding and works like GPT-3 for natural language generation are very important. If we consider DNA sequences as a text written with an alphabet of four letters representing the nucleotides, they are similar in structure to natural languages. This similarity has led to the development of discriminative language models such as DNABERT in the field of DNA-related bioinformatics. To our knowledge, however, the generative side of the coin is still largely unexplored. Therefore, we have focused on the development of an autoregressive generative language model such as GPT-3 for DNA sequences. Since working with whole DNA sequences is challenging without extensive computational resources, we decided to conduct our study on a smaller scale and focus on nucleotide sequences of human genes, i.e. unique parts of DNA with specific functions, rather than the whole DNA. This decision has not significantly changed the structure of the problem, as both DNA and genes can be considered as 1D sequences consisting of four different nucleotides without losing much information and without oversimplification. First of all, we systematically studied an almost entirely unexplored problem and observed that recurrent neural networks (RNNs) perform best, while simple techniques such as N-grams are also promising. Another beneficial point was learning how to work with generative models on languages we do not understand, unlike natural languages. The importance of using real-world tasks beyond classical metrics such as perplexity was noted. In addition, we examined whether the data-hungry nature of these models can be altered by selecting a language with minimal vocabulary size, four due to four different types of nucleotides. The reason for reviewing this was that choosing such a language might make the problem easier. However, in this study, we found that this did not change the amount of data required very much.

Privacy-Enhanced Prototype-Based Federated Cross-Modal Hashing for Cross-Modal Retrieval

Cross-modal hashing is widely used for efficient similarity searches, improving data processing efficiency, and reducing storage costs. Existing cross-modal hashing methods primarily focus on centralized training scenarios, where fixed-scale and fixed-category multi-modal data is collected beforehand. However, these methods often face challenges associated with the potential risk of privacy breaches and high data communication costs during data transmission in real-world multimedia retrieval tasks. To tackle these challenges, in this article, we propose an efficient privacy-enhanced prototype-based federated cross-modal hashing (PEPFCH). In PEPFCH, we integrate local and global prototypes in order to effectively capture the distinctive traits of individual clients, while also harnessing the collective intelligence of the entire federated learning system. Moreover, to ensure the security of prototype information and prevent its disclosure during the aggregation process, we use a prototype encryption transmission mechanism to encrypt the prototype information before transmission, making it challenging for attackers to gain access to sensitive data. Additionally, to facilitate personalized federated learning and alleviate the issue of parametric catastrophic forgetting, we establish the image and text hyper-networks for each client and adopt a hyper-network extension strategy to selectively preserve and update previously acquired knowledge when acquiring new concepts or categories. Comprehensive experiments highlight the efficiency and superiority of our proposed method. To enhance research and accessibility, we have publicly released our source codes at: https://github.com/vindahi/PEPFCH .

Models optimized for real-world tasks reveal the task-dependent necessity of precise temporal coding in hearing.

Neurons encode information in the timing of their spikes in addition to their firing rates. Spike timing is particularly precise in the auditory nerve, where action potentials phase lock to sound with sub-millisecond precision, but its behavioral relevance remains uncertain. We optimized machine learning models to perform real-world hearing tasks with simulated cochlear input, assessing the precision of auditory nerve spike timing needed to reproduce human behavior. Models with high-fidelity phase locking exhibited more human-like sound localization and speech perception than models without, consistent with an essential role in human hearing. However, the temporal precision needed to reproduce human-like behavior varied across tasks, as did the precision that benefited real-world task performance. These effects suggest that perceptual domains incorporate phase locking to different extents depending on the demands of real-world hearing. The results illustrate how optimizing models for realistic tasks can clarify the role of candidate neural codes in perception.

Practically implementing an LLM-supported collaborative vulnerability remediation process: A team-based approach

Incorporating LLM into cybersecurity operations, a typical real-world high-stakes task, is critical but non-trivial in practice. Using cybersecurity as the study context, we conduct a three-step mix-method study to incorporate LLM into the vulnerability remediation process effectively. Specifically, we deconstruct the deficiencies in user satisfaction within the existing process (Study 1). This inspires us to design, implement, and empirically validate an LLM-supported collaborative vulnerability remediation process through a field study (Study 2). Given LLM’s diverse contributions, we further investigate LLM’s double-edge roles through the analysis of remediation reports and follow-up interviews (Study 3). In essence, our contribution lies in promoting an efficient LLM-supported collaborative vulnerability remediation process. These first-hand, real-world pieces of evidence suggest that when incorporating LLMs into practical processes, facilitating the collaborations among all associated stakeholders, reshaping LLMs’ roles according to task complexity, as well as approaching the short-term side effects of improved user engagement facilitated by LLMs with a rational mindset.

Behavioral Alterations of Spatial Cognition and Role of the Apolipoprotein E-ε4 in Patients with MCI Due to Alzheimer's Disease: Results from the BDSC-MCI Project.

Background: Beyond memory deterioration, spatial disorientation may occur along the continuum of normal aging-dementia of Alzheimer's type. The present study aims at detecting behavioral disorders of spatial cognition in prodromal Alzheimer's disease (AD) and verifying the association between Apolipoprotein E-ε4 (ApoE-ε4) genotype and gait patterns during a real-world naturalistic task. Methods: A sample of 58 elderly participants, of which 20 patients with mild cognitive impairment with CFS biomarker evidence of AD, 23 individuals with subjective cognitive decline (SCD), and 15 healthy controls (HCs), was tested by a modified version of the Detour Navigation Test (DNT-mv). Generalized linear models were run to explore the association between group belonging and wrong turns (WTs)/moments of hesitation (MsH) as behavioral disorientation scores of the DNT-mv as well as the effect of ApoE-ε4 genotype on time and walking speed registered by a smartphone app providing GPS tracking of body movement around urban environments. Results: Patients with MCI due to AD reported more WTs than individuals with SCD and HCs. Further, the ApoE-ε4 genotype determined a lower capacity in spatial information processing, influencing gait during naturalistic spatial navigation tasks. Conclusions: Behavior alterations of spatial cognition can be detected ecologically in prodromal AD. The use of technological solutions supporting gait analysis may help in corroborating the experimental observation.

A - 85 Age-Related Differences in Cognitive Mechanisms: Exploring the Role of Processing Speed in Working Memory and Prospective Memory

Abstract Objective Research links working memory (WM) and prospective memory (PM) on cognitively demanding tasks. Older adults demonstrate more frontal lobe activation than young adults during WM and PM tasks; however, the underlying mechanisms remain unclear. The current study hypothesized processing speed (PS) as a mediator between WM and PM with age cohort as a possible moderator. Method Healthy older adults (n = 80; age 60–89, M = 72.51, SD = 7.08) and young adults (n = 63; age 18–29, M = 19.27, SD = 2.12) were administered WAIS-IV Digit Span, WAIS-IV Coding, and the Virtual Kitchen Protocol for Prospective Memory. Results A moderated mediation model revealed that WM positively influenced PM (c:B = 0.69, p < 0.001) with a positive indirect relationship through PS among older adults (ab:B = 0.26, 95% CI [0.13, 0.43]), but not young adults (ab:B = −0.08, 95% CI [−0.19, 0.03]). Conclusion PS appears to play a significant role in older adults’ use of WM for PM but not in young adults. This could suggest that older adults recruit additional cognitive resources – those involved in PS – as a compensatory strategy for real-world PM tasks, which would support prior research indicating that diminished functioning in older adults results from reduced ability to redirect neurocognitive networks. Alternatively, age-related declines in PS could be a root cause underlying both worse WM and worse PM in older adults, as postulated by Salthouse. Future research would benefit from further differentiating the direction of influences between WM, PS, and PM in older adults.

Encoding innate ability through a genomic bottleneck

Animals are born with extensive innate behavioral capabilities, which arise from neural circuits encoded in the genome. However, the information capacity of the genome is orders of magnitude smaller than that needed to specify the connectivity of an arbitrary brain circuit, indicating that the rules encoding circuit formation must fit through a "genomic bottleneck" as they pass from one generation to the next. Here, we formulate the problem of innate behavioral capacity in the context of artificial neural networks in terms of lossy compression of the weight matrix. We find that several standard network architectures can be compressed by several orders of magnitude, yielding pretraining performance that can approach that of the fully trained network. Interestingly, for complex but not for simple test problems, the genomic bottleneck algorithm also captures essential features of the circuit, leading to enhanced transfer learning to novel tasks and datasets. Our results suggest that compressing a neural circuit through the genomic bottleneck serves as a regularizer, enabling evolution to select simple circuits that can be readily adapted to important real-world tasks. The genomic bottleneck also suggests how innate priors can complement conventional approaches to learning in designing algorithms for AI.

Bilateral Proxy Federated Domain Generalization for Privacy-preserving Medical Image Diagnosis.

Contemporary domain generalization methods have demonstrated effectiveness in aiding the generalized diagnosis of medical images with multi-source data by joint optimization. However, the centralized training paradigm employed by these approaches becomes infeasible when data are non-shared across domains due to the high privacy of medical data. Despite attempts by existing federated domain generalization methods to address this issue, the simultaneous attainment of strict privacy protection and a satisfactory level of generalization ability on out-of-distribution data remains a persistent challenge. In this paper, to tackle this challenging problem, we propose a novel approach called the Bilateral Proxy Framework (BPF). The BPF leverages the client-side proxies to facilitate the strict privacy-preserving communications with the server and ensure smoother and more stable convergences of local models through mutual distillation. Meanwhile, the server-side proxy adopts a distance-based strategy and a parameter moving average scheme, which enhances the stability and robustness of the global model, particularly by averting abrupt parameter changes that could result in fluctuations or overfitting. Through these advancements, our framework strives to enhance the generalization capability of the global model, enabling more accurate and reliable medical image diagnosis in federated settings. The effectiveness of our method is demonstrated with superior performance over state-of-the-arts on both simulated and real-world distribution medical image diagnosis tasks.

Validating, Implementing, and Monitoring Machine Learning Solutions in the Clinical Laboratory Safely and Effectively.

Machine learning solutions offer tremendous promise for improving clinical and laboratory operations in pathology. Proof-of-concept descriptions of these approaches have become commonplace in laboratory medicine literature, but only a scant few of these have been implemented within clinical laboratories, owing to the often substantial barriers in validating, implementing, and monitoring these applications in practice. This mini-review aims to highlight the key considerations in each of these steps. Effective and responsible applications of machine learning in clinical laboratories require robust validation prior to implementation. A comprehensive validation study involves a critical evaluation of study design, data engineering and interoperability, target label definition, metric selection, generalizability and applicability assessment, algorithmic fairness, and explainability. While the main text highlights these concepts in broad strokes, a supplementary code walk-through is also provided to facilitate a more practical understanding of these topics using a real-world classification task example, the detection of saline-contaminated chemistry panels.Following validation, the laboratorian's role is far from over. Implementing machine learning solutions requires an interdisciplinary effort across several roles in an organization. We highlight the key roles, responsibilities, and terminologies for successfully deploying a validated solution into a live production environment. Finally, the implemented solution must be routinely monitored for signs of performance degradation and updated if necessary. This mini-review aims to bridge the gap between theory and practice by highlighting key concepts in validation, implementation, and monitoring machine learning solutions effectively and responsibly in the clinical laboratory.

Comparative analysis of saliency map algorithms in capturing visual priorities for building inspections

This study investigates the efficacy of saliency mapping algorithms in capturing the visual priorities of building inspectors for structural damage assessment. Our work established a ground truth dataset by implementing eye-tracking technology to capture the gaze patterns of building inspectors. Further, it enables a detailed evaluation of the saliency models’ ability to reflect experts' visual attention during inspection tasks. Our comparative analysis assesses the performance of three saliency models— EnDec, DeepGaze, and SALICON— against this ground truth data, using conventional saliency metrics such as Area under the Curve, Similarity, Normalized Scanpath Saliency, Correlation Coefficient, and Kullback-Leibler Divergence. Our findings reveal that while the SALICON model demonstrates a marginally better performance and highlights areas where these models fall short, particularly in accurately reflecting the critical visual properties of inspectors, this insight is crucial for advancing the field. By highlighting these limitations, we have drawn attention to the need for developing more specialized saliency models tailored to the unique demands of building inspection tasks. Thus, the study not only fulfills its objectives of comparative analysis but also contributes to the broader discourse on improving automated structural inspection systems. This study highlights the need to develop specialized computer vision models to address specific building inspection challenges. By identifying strengths and improvement areas, this research contributes valuable insights and highlights the potential and current limitations of applying computer vision techniques to real-world building inspection tasks.

Orthophoto-Based Vegetation Patch Analyses—A New Approach to Assess Segmentation Quality

The following paper focuses on evaluating the quality of image prediction in the context of searching for plants of a single species, using the example of Heracleum sosnowskyi Manden, in a given area. This process involves a simplified classification that ends with a segmentation step. Because of the particular characteristics of environmental data, such as large areas of plant occurrence, significant partitioning of the population, or characteristics of a single individual, the use of standard statistical measures such as Accuracy, the Jaccard Index, or Dice Coefficient does not produce reliable results, as shown later in this study. This issue demonstrates the need for a new method for assessing the betted prediction quality adapted to the unique characteristics of vegetation patch detection. The main aim of this study is to provide such a metric and demonstrate its usefulness in the cases discussed. Our proposed metric introduces two new coefficients, M+ and M−, which, respectively, reward true positive regions and penalise false positive regions, thus providing a more nuanced assessment of segmentation quality. The effectiveness of this metric has been demonstrated in different scenarios focusing on variations in spatial distribution and fragmentation of theoretical vegetation patches, comparing the proposed new method with traditional metrics. The results indicate that our metric offers a more flexible and accurate assessment of segmentation quality, especially in cases involving complex environmental data. This study aims to demonstrate the usefulness and applicability of the metric in real-world vegetation patch detection tasks.