Threat-induced prosocial behavior: enhanced exogenous attention to protect others from harm.

As social animals, humans tend to voluntarily engage in pro-social behavior to prevent harm to others. However, to what extent prosocial behavior can be reflected at the level of less voluntary cognitive processes remains unclear. Here, we examined how threat to others modulates exogenous attention. Fifty-four participants performed an exogenous spatial cueing task where the participant's performance determined whether electric shocks would be delivered either to themselves or to their anonymous co-participant. Threat of shock to the co-participant elicited orienting and reorienting responses that were faster than in the safe condition and did not differ from performance when participants avoided shocks to themselves. This attentional improvement was not due to speed-accuracy trade off and was associated with arousal, i.e., increased pupil dilation in both threat conditions. Together, these findings suggest that pro-social behavior triggers automatic attentional processes which may be relevant for providing immediate help without relying on reflexive processes.

"We do others' Jobs": a qualitative study of non-nursing task challenges and proposed solutions.

INTRODUCTION: Non-nursing tasks (NNTs) have become a prevalent issue among healthcare professionals, affecting nurses globally. This study delves into the experiences of Jordanian nurses regarding NNTs, aiming to uncover challenges and propose solutions within the Jordanian healthcare context. OBJECTIVE: Explore the impact of NNTs on Jordanian nurses' roles, workload, and satisfaction. Additionally, the study aims to identify various types of NNTs performed by nurses, understand their impact, and propose solutions to mitigate challenges associated with these tasks. METHODS: A qualitative-exploratory research design was employed for this study. Semi-structured interviews were conducted with Jordanian nurses using a purposeful sampling approach to ensure a diverse representation of experiences and perspectives. Thematic analysis was used to identify recurring themes and patterns related to NNTs, their challenges, and potential solutions. Ethical guidelines were strictly followed to maintain participant confidentiality and ensure the integrity of the data collected. RESULTS: Analysis of the interviews revealed four major themes: challenges of NNTs, types of NNTs, impact of NNTs, and proposed solutions. Nurses faced significant difficulties due to task ambiguity, role confusion, and increased workload from NNTs, which included administrative duties, clerical work, and tasks typically performed by other healthcare professionals. These NNTs negatively impacted nurses' effectiveness, productivity, and job satisfaction by diverting time and energy from primary nursing responsibilities, causing professional strain. To address these issues, participants suggested clearer job descriptions, stricter task assignment protocols, and systemic changes to tackle the root causes of NNTs. CONCLUSION: This study sheds light on the pervasive challenges posed by NNTs among Jordanian nurses and emphasizes the importance of addressing these issues to enhance nursing care quality and nurse well-being. By proposing actionable solutions tailored to the Jordanian context, this research contributes to the global discourse on NNTs and underscores the need for organizational support and advocacy to optimize nurses' roles and improve patient care outcomes.

Task and stimulus coding in the multiple-demand network.

In the human brain, a multiple-demand (MD) network plays a key role in cognitive control, with core components in lateral frontal, dorsomedial frontal and lateral parietal cortex, and multivariate activity patterns that discriminate the contents of many cognitive activities. In prefrontal cortex of the behaving monkey, different cognitive operations are associated with very different patterns of neural activity, while details of a particular stimulus are encoded as small variations on these basic patterns (Sigala et al, 2008). Here, using the advanced fMRI methods of the Human Connectome Project and their 360-region cortical parcellation, we searched for a similar result in MD activation patterns. In each parcel, we compared multivertex patterns for every combination of three tasks (working memory, task-switching, and stop-signal) and two stimulus classes (faces and buildings). Though both task and stimulus category were discriminated in every cortical parcel, the strength of discrimination varied strongly across parcels. The different cognitive operations of the three tasks were strongly discriminated in MD regions. Stimulus categories, in contrast, were most strongly discriminated in a large region of primary and higher visual cortex, and intriguingly, in both parietal and frontal lobe regions adjacent to core MD regions. In the monkey, frontal neurons show a strong pattern of nonlinear mixed selectivity, with activity reflecting specific conjunctions of task events. In our data, however, there was limited evidence for mixed selectivity; throughout the brain, discriminations of task and stimulus combined largely linearly, with a small nonlinear component. In MD regions, human fMRI data recapitulate some but not all aspects of electrophysiological data from nonhuman primates.

An interpretable two-branch bi-coordinate network based on multi-grained domain knowledge for classification of thyroid nodules in ultrasound images.

Computer-aided diagnosis (CAD) for thyroid nodules has been studied for years, yet there are still reliability and interpretability challenges due to the lack of clinically-relevant evidence. To address this issue, inspired by Thyroid Imaging Reporting and Data System (TI-RADS), we propose a novel interpretable two-branch bi-coordinate network based on multi-grained domain knowledge. First, we transform the two types of domain knowledge provided by TI-RADS, namely region-based and boundary-based knowledge, into labels at multi-grained levels: coarse-grained classification labels, and fine-grained region segmentation masks and boundary localization vectors. We combine these two labels to form the Multi-grained Domain Knowledge Representation (MG-DKR) of TI-RADS. Then we design a Two-branch Bi-coordinate network (TB2C-net) which utilizes two branches to predict MG-DKR from both Cartesian and polar images, and uses an attention-based integration module to integrate the features of the two branches for benign-malignant classification. We validated our method on a large cohort containing 3245 patients (with 3558 nodules and 6466 ultrasound images). Results show that our method achieves competitive performance with AUC of 0.93 and ACC of 0.87 compared with other state-of-the-art methods. Ablation experiment results demonstrate the effectiveness of the TB2C-net and MG-DKR, and the knowledge attention map from the integration module provides the interpretability for benign-malignant classification.

Effectiveness, acceptability, and potential of lay student vaccinators to improve vaccine delivery.

SETTING: Task sharing can fill health workforce gaps, improve access to care, and enhance health equity by redistributing health services to providers with less training. We report learnings from a demonstration project designed to assess whether lay student vaccinators can support community immunizations. INTERVENTION: Between July 2022 and February 2023, 27 undergraduate and graduate students were recruited from the University of Toronto Emergency First Responders organization and operated 11 immunization clinics under professional supervision. Medical directives, supported with online and in-person training, enabled lay providers to administer and document vaccinations when supervised by nurses, physicians, or pharmacists. Participants were invited to complete a voluntary online survey to comment on their experience. OUTCOMES: Lay providers administered 293 influenza and COVID-19 vaccines without adverse events. A total of 141 participants (122 patients, 17 lay vaccinators, 1 nurse, and 1 physician) responded to our survey. More than 80% of patients strongly agreed to feeling safe and comfortable with lay providers administering vaccines under supervision, had no concerns with lay vaccinators, and would attend another lay vaccinator clinic. Content and thematic analysis of open-text responses revealed predominantly positive experiences, with themes about excellent vaccinators, organized and efficient clinics, and the importance of training, communication, and access to regulated professionals. The responding providers expressed comfort working in collaborative immunization teams. IMPLICATIONS: Lay student providers can deliver vaccines safely under a medical directive while potentially improving patient experiences. Rather than redeploying scarce professionals, task sharing strategies could position trained lay vaccinators to support immunizations, improve access, and foster community engagement.

RéSUMé: LIEU: Le partage de tâches peut combler les pénuries de personnels de santé et améliorer l'accès aux soins et l'équité en santé en redistribuant les services de santé vers des prestataires ayant moins de formation. Nous rendons compte des enseignements d'un projet de démonstration visant à déterminer si des vaccinateurs étudiants profanes pourraient appuyer l'immunisation communautaire. INTERVENTION: Entre juillet 2022 et février 2023, 27 étudiantes et étudiants de premier cycle et de cycles supérieurs ont été recrutés auprès de l'organisation des secouristes opérationnels de l'Université de Toronto pour gérer 11 cliniques de vaccination sous la supervision de personnel spécialisé. Des directives médicales, appuyées par une formation en ligne et en présentiel, ont permis à ces prestataires profanes d'administrer des vaccins et de les consigner en dossier sous la supervision d'infirmières, de médecins ou de pharmaciens. Les personnes participantes ont été invitées à répondre à un sondage en ligne sur leur expérience. RéSULTATS: Les prestataires profanes ont administré 293 vaccins contre la grippe et la COVID-19 sans manifestations postvaccinales indésirables. En tout, 141 personnes (122 patients, 17 vaccinateurs profanes, 1 infirmière et 1 médecin) ont répondu au sondage. Plus de 80 % des patients ont dit se sentir tout à fait en sécurité et à l'aise de recevoir des vaccins administrés par des prestataires profanes sous supervision, n'avoir aucune inquiétude vis-à-vis des vaccinateurs profanes et être disposés à se présenter à une autre clinique gérée par des vaccinateurs profanes. L'analyse du contenu et des thèmes des réponses aux questions ouvertes a révélé des expériences majoritairement positives, et des thèmes axés sur l'excellence des vaccinateurs, l'organisation et l'efficacité des cliniques, ainsi que l'importance de la formation, des communications et de l'accès à des professionnels réglementés. Les prestataires ayant répondu au sondage se sont dit à l'aise de travailler au sein d'équipes de vaccination collaboratives. CONSéQUENCES: Des prestataires étudiants profanes peuvent administrer des vaccins en toute sécurité en suivant une directive médicale, et cela peut potentiellement améliorer l'expérience des patients. Plutôt que de redéployer des ressources professionnelles limitées, les stratégies de partage de tâches pourraient placer des vaccinateurs profanes formés pour appuyer l'immunisation, améliorer l'accès et favoriser l'engagement communautaire.

Strategic and self-regulated instruction in synthesis tasks in the university context.

Introduction: The aim of the study was to improve student skills in writing good-quality synthesis texts through a strategic, self-regulated instruction program aimed at ensuring that students properly activated reading and writing strategies required by the synthesis task. Methods: The sample consisted of 84 university students who were randomly assigned to experimental or control conditions. The experimental group received an instructional program based on the development and self-regulated implementation of reading and writing strategies for producing synthesis texts. The control group received a program involving metacognitive knowledge of various academic text types. Both programs involved eight 60-min sessions, taught by teachers in a compulsory degree subject. For the evaluations, students produced synthesis texts from different source texts. The syntheses were graded considering text product measures: information selection, idea connection, text organization, and holistic quality; and measures of reading (underlining and note-taking) and writing (planning and review) strategies. Results: The results show that the experimental group exhibited greater improvements in synthesis quality and greater improvements in activation of information organization processes, note-taking while reading, and text planning. Discussion: In conclusion, university students can, following implementation of a strategic instructional procedure in the context of a study plan, adapt and re-work their own reading and writing strategies and apply them in a self-regulated manner to synthesis tasks, improving text quality and some of the cognitive processes involved.

Universal mental health training for frontline professionals: evaluation of pilot trial in Ukraine.

Background: Increasing accessibility of mental health services and expanding universal health coverage is possible worldwide by using a task-shifting approach as partial delegation of some mental health support tasks to trained non-mental health service providers in order to use the available workforce more efficiently. The Universal Mental Health Training (UMHT), which is dedicated to this aim, was developed and piloted in Ukraine. The UMHT is an educational program for frontline professionals on high-quality and evidence-based responses to the mental health needs of the population they serve. Methods: The pilot trial of UMHTs' effectiveness was conducted with 307 frontline professionals divided into 24 training groups. The control group included 211 persons with the same occupation background who participated in training later (waiting list). All the groups took part in eight-hour training, which includes one introductory module that introduces the mental health topic alongside a five-step model of UMHT, two disorders-focused modules with the steps adjusted to work with specific disorders, and the final module that considers possible difficulties frontline professionals might experience. Three effectiveness measurements were used in the outcome assessment: readiness to interact with people with mental health issues at work, mental health awareness and mental health proficiency. Results: Analysis of the outcome data for the frontline professionals who underwent the UMHT revealed a moderate effect size related to the knowledge of mental health conditions, mental health awareness, and increasing the readiness to interact with people with mental health issues in comparison to the control group. Conclusions: High-level utilisation of the UMHT at work by trained professionals confirms the effectiveness of the developed intervention. Obtained results favour the continuation of the development of the UMHT and future implementation research in this field in Ukraine and potentially in other low- and middle-income countries.

Perceptual decoupling in the sustained attention to response task is unlikely.

Researchers dispute the cause of errors in high Go, low No Go target detection tasks, like the Sustained Attention to Response Task (SART). Some researchers propose errors in the SART are due to perceptual decoupling, where a participant is unaware of stimulus identity. This lack of external awareness causes an erroneous response. Other researchers suggest the majority of the errors in the SART are instead due to response leniency, not perceptual decoupling. Response delays may enable a participant who is initially unaware of stimulus identity, perceptually decoupled, to become aware of stimulus identity, or perceptually recoupled. If, however, the stimulus presentation time is shortened to the minimum necessary for stimulus recognition and the stimulus is disrupted with a structured mask, then there should be no time to enable perception to recouple even with a response delay. From the perceptual decoupling perspective, there should be no impact of a response delay on performance in this case. Alternatively if response bias is critical, then even in this case a response delay may impact performance. In this study, we shortened stimulus presentation time and added a structured mask. We examined whether a response delay impacted performance in the SART and tasks where the SART's response format was reversed. We expected a response delay would only impact signal detection theory bias, c, in the SART, where response leniency is an issue. In the reverse formatted SART, since bias was not expected to be lenient, we expected no impact or minimal impact of a response delay on response bias. These predictions were verified. Response bias is more critical in understanding SART performance, than perceptual decoupling, which is rare if it occurs at all in the SART.

The antisaccadic paradigm: A complementary neuropsychological tool in basal ganglia disorders.

This review explores the role of the antisaccadic task in understanding inhibitory mechanisms in basal ganglia disorders. It conducts a comparative analysis of saccadic profiles in conditions such as Parkinson's disease, Tourette syndrome, obsessive-compulsive disorder, Huntington's disease, and dystonia, revealing distinct patterns and proposing mechanisms for impaired performance. The primary focus is on two inhibitory mechanisms: global, pre-emptive inhibition responsible for suppressing prepotent responses, and slower, selective response inhibition. The antisaccadic task demonstrates practicality in clinical applications, aiding in differential diagnoses, treatment monitoring and reflecting gait control. To further enhance its differential diagnostic value, future directions should address issues such as the standardization of eye-tracking protocol and the integration of eye-tracking data with other disease indicators in a comprehensive dataset.

Dorsiflexion Specific Ankle Robotics to Enhance Motor Learning After Stroke: A Preliminary Report.

Background: Robotics has emerged as a promising avenue for gait retraining of persons with chronic hemiparetic gait and footdrop, yet there is a gap regarding the biomechanical adaptations that occur with locomotor learning. We developed an ankle exoskeleton (AMBLE) enabling dorsiflexion assist-as-needed across gait cycle sub-events to train and study the biomechanics of motor learning stroke. This single-armed, non-controlled study investigates effects of nine hours (9 weeks × 2 sessions/week) locomotor task-specific ankle robotics training on gait biomechanics and functional mobility in persons with chronic hemiparetic gait and foot drop. Subjects include N = 16 participants (8 male, 8 female) age 53 ± 12 years with mean 11 ± 8 years since stroke. All baseline and post-training outcomes including optical motion capture for 3-D gait biomechanics are conducted during unassisted (no robot) over-ground walking conditions. Findings: Robotics training with AMBLE produced significant kinematic improvements in ankle peak dorsiflexion angular velocity (°/s, + 44 [49%], p < 0.05), heel-first foot strikes (%steps, + 14 [15%], p < 0.01) toe-off angle (°, + 83[162%], p < 0.05), and paretic knee flexion (°, + 20 [30%], p < 0.05). Improvements in gait temporal-spatial parameters include increased paretic step length (cm, + 12 [20%], p< 0.05), reduced paretic swing duration (%GC, -3[6%], p < 0.05), and trend toward improved step length symmetry (-16 [11%], p = 0.08). Functional improvements include 10-meter comfortable (m/s, + 13 [16%], p < 0.01) and fastest (m/s, + 13 [15%], p<0.01) walking velocities, 6-minute timed walk distance (m, + 16 [19%], p < 0.01) and Dynamic Gait Index scores (+15 [15%], p < 0.01). Subjects' perceived improvements surpassed the minimal clinically important difference on the Stroke Impact Scale (SIS) mobility subscale (+11 [19%], p < 0.05). Conclusions: AMBLE training improves paretic ankle neuromotor control, paretic knee flexion, and gait temporal-distance parameters during unassisted over-ground walking in persons with chronic stroke and foot drop. This locomotor learning indexed by an increase in volitional autonomous (non-robotic) control of paretic ankle across training translated to improvements in functional mobility outcomes. Larger randomized clinical trials are needed to investigate the effectiveness of task-specific ankle robotics, and precise training characteristics to durably improve gait, balance, and home and community-based functional mobility for persons with hemiparetic gait and foot drop. Clinical trial identifier: NCT04594837.

The impact of sleep quality on visual working memory varied with the duration of maintenance.

Objective: Sleep quality can affect the performance of visual working memory. However, the effect of sleep quality on the maintenance stage, which is the key to maintain the quality and efficiency of visual working memory representation, remains unclear. This study is the first to explore the effect of sleep quality on the maintenance of visual working memory information. Method: 60 healthy college students completed the Pittsburgh Sleep Quality Index (PSQI) and color recall task of visual working memory. A mixed experimental design of sleep quality (high or low) and delay duration (1, 4, or 6 s) was used to assess the effect of sleep quality on the maintenance phase of visual working memory. Results: The main effects of sleep quality were significant on visual working memory quantity, precision and offset indexes. Among the quantity index, the interaction between sleep quality and delay duration was also significant. This suggests that prolonging the delay time in the maintenance phase leads to difficulty in maintaining attention to the task for those with lower sleep quality, which results in poorer working memory quantitative representations. Conclusion: Increases in the delay duration of the maintenance phase in visual working memory intensify the impact of sleep quality on task performance. Our study provides evidence to reveal the relationship between sleep quality and visual working memory and offers recommendations for improving sleep quality and cognitive functioning in individuals.

Deep reinforcement learning task scheduling method based on server real-time performance.

Server load levels affect the performance of cloud task execution, which is rooted in the impact of server performance on cloud task execution. Traditional cloud task scheduling methods usually only consider server load without fully considering the server's real-time load-performance mapping relationship, resulting in the inability to evaluate the server's real-time processing capability accurately. This deficiency directly affects the efficiency, performance, and user experience of cloud task scheduling. Firstly, we construct a performance platform model to monitor server real-time load and performance status information in response to the above problems. In addition, we propose a new deep reinforcement learning task scheduling method based on server real-time performance (SRP-DRL). This method introduces a real-time performance-aware strategy and adds status information about the real-time impact of task load on server performance on top of considering server load. It enhances the perception capability of the deep reinforcement learning (DRL) model in cloud scheduling environments and improves the server's load-balancing ability under latency constraints. Experimental results indicate that the SRP-DRL method has better overall performance regarding task average response time, success rate, and server average load variance compared to Random, Round-Robin, Earliest Idle Time First (EITF), and Best Fit (BEST-FIT) task scheduling methods. In particular, the SRP-DRL is highly effective in reducing server average load variance when numerous tasks arrive within a unit of time, ultimately optimizing the performance of the cloud system.

Lavender Essential Oil Inhalation Improves Attentional Shifting and Accuracy: Evidence from Dynamic Changes of Cognitive Flexibility and Power Spectral Density of Electroencephalogram Signals.

Background: Cognitive flexibility, a vital component of executive function, entails the utilization of extended brain networks. Olfactory stimulation has been shown to influence various brain functions, particularly cognitive performance. Method: To investigate aroma inhalation's effects on brain activity dynamics associated with cognitive flexibility, 20 healthy adults were recruited to complete a set-shifting task during two experimental conditions: no aroma stimuli vs. lavender essential oil inhalation. Using Thomson's multitaper approach, the normalized power spectral density (NPSD) was assessed for five frequency bands. Results: Findings confirm that aroma inhalation significantly affects behavioral indices (i.e., reaction time (RT) and response accuracy) and electroencephalogram (EEG) signatures, especially in the frontal lobe. Participants showed a tremendous increase in theta and alpha NPSD, associated with relaxation, along with beta NPSD, associated with clear and fast thinking after inhaling the aroma. NPSD of the delta band, an indicator of the unconscious mind, significantly decreased when stimulated with lavender essential oil. Further, participants exhibited shorter RT and more accurate responses following aroma inhalation. Conclusion: Our findings revealed significant changes in oscillatory power and behavioral performance after aroma inhalation, providing neural evidence that olfactory stimulation with lavender essential oil may facilitate cognitive flexibility.

Impact of task-oriented training based on acupuncture rehabilitation on upper extremity function and quality of life of patients with early stroke.

BACKGROUND: Eighty percent of stroke patients develop upper limb dysfunction, especially hand dysfunction, which has a very slow recovery, resulting in economic burden to families and society. AIM: To investigate the impact of task-oriented training based on acupuncture therapy on upper extremity function in patients with early stroke. METHODS: Patients with early stroke hemiplegia who visited our hospital between January 2021 and October 2022 were divided into a control group and an observation group, each with 50 cases. The control group underwent head acupuncture plus routine upper limb rehabilitation training (acupuncture therapy). In addition to acupuncture and rehabilitation, the observation group underwent upper limb task-oriented training (30 min). Each group underwent treatment 5 d/wk for 4 wk. Upper extremity function was assessed in both groups using the Fugl-Meyer Assessment-Upper Extremity (FMA-UE), Wolf Motor Function Rating Scale (WMFT), modified Barthel Index (MBI), and Canadian Occupational Performance Measure (COPM). Quality of life was evaluated using the Short-Form 36-Item Health Survey (SF-36). Clinical efficacy of the interventions was also evaluated. RESULTS: Before intervention, no significant differences were observed in the FMA-UE, MBI, and WMFT scores between the two groups (P > 0.05). After intervention, the FMA-UE, WMFT, MBI, COPM-Functional Mobility and Satisfaction, and SF-36 scores increased in both groups (P < 0.05), with even higher scores in the observation group (P < 0.05). The observation group also obtained a higher total effective rate than the control group (P < 0.05). CONCLUSION: Task-oriented training based on acupuncture rehabilitation significantly enhanced upper extremity mobility, quality of life, and clinical efficacy in patients with early stroke.

Cognitive-motor dual task to reveal gait impairments in multiple sclerosis patients at an early stage: A systematic review.

BACKGROUND: Multiple sclerosis can cause locomotor and cognitive impairments even at lower levels of disability, which can impact daily life. The cognitive-motor dual task is commonly used to assess everyday locomotion. Thus, this study aimed to examine the effect of cognitive-motor dual tasks on gait parameters among patients with multiple sclerosis in the early disease stages and to determine whether dual tasks could be used as a clinical test to detect locomotion impairments. METHODS: A systematic search of five databases was conducted in May 2024. The population of interest was patients with multiple sclerosis with an Expanded Disability Status Scale score of 4 or less. The following outcome measures were examined: spatiotemporal and kinematic parameters. The Newcastle-Ottawa Scale was used to assess the quality of the studies. FINDINGS: Eleven studies including 270 patients with multiple sclerosis and 221 healthy controls. Three spatiotemporal parameters were modified both in patients with multiple sclerosis and healthy controls during dual-task performance: gait speed, stride length and the double support phase. No spatiotemporal parameter was affected during dual-task performance in patients with multiple sclerosis alone. INTERPRETATION: Dual-task performance could be useful for assessing gait impairments in patients with multiple sclerosis provided that assessments and protocols are standardized. Nevertheless, the spatiotemporal parameters did not allow discrimination between patients with multiple sclerosis at an early stage and healthy controls. Three-dimensional gait analysis during dual-task performance could be a useful approach for detecting early gait impairments in patients with multiple sclerosis, assessing their progression and adjusting rehabilitation programs.

ProPept-MT: A Multi-Task Learning Model for Peptide Feature Prediction.

In the realm of quantitative proteomics, data-independent acquisition (DIA) has emerged as a promising approach, offering enhanced reproducibility and quantitative accuracy compared to traditional data-dependent acquisition (DDA) methods. However, the analysis of DIA data is currently hindered by its reliance on project-specific spectral libraries derived from DDA analyses, which not only limits proteome coverage but also proves to be a time-intensive process. To overcome these challenges, we propose ProPept-MT, a novel deep learning-based multi-task prediction model designed to accurately forecast key features such as retention time (RT), ion intensity, and ion mobility (IM). Leveraging advanced techniques such as multi-head attention and BiLSTM for feature extraction, coupled with Nash-MTL for gradient coordination, ProPept-MT demonstrates superior prediction performance. Integrating ion mobility alongside RT, mass-to-charge ratio (m/z), and ion intensity forms 4D proteomics. Then, we outline a comprehensive workflow tailored for 4D DIA proteomics research, integrating the use of 4D in silico libraries predicted by ProPept-MT. Evaluation on a benchmark dataset showcases ProPept-MT's exceptional predictive capabilities, with impressive results including a 99.9% Pearson correlation coefficient (PCC) for RT prediction, a median dot product (DP) of 96.0% for fragment ion intensity prediction, and a 99.3% PCC for IM prediction on the test set. Notably, ProPept-MT manifests efficacy in predicting both unmodified and phosphorylated peptides, underscoring its potential as a valuable tool for constructing high-quality 4D DIA in silico libraries.

A Multi-Task Joint Learning Model Based on Transformer and Customized Gate Control for Predicting Remaining Useful Life and Health Status of Tools.

Previous studies have primarily focused on predicting the remaining useful life (RUL) of tools as an independent process. However, the RUL of a tool is closely related to its wear stage. In light of this, a multi-task joint learning model based on a transformer encoder and customized gate control (TECGC) is proposed for simultaneous prediction of tool RUL and tool wear stages. Specifically, the transformer encoder is employed as the backbone of the TECGC model for extracting shared features from the original data. The customized gate control (CGC) is utilized to extract task-specific features relevant to tool RUL prediction and tool wear stage and shared features. Finally, by integrating these components, the tool RUL and the tool wear stage can be predicted simultaneously by the TECGC model. In addition, a dynamic adaptive multi-task learning loss function is proposed for the model's training to enhance its calculation efficiency. This approach avoids unsatisfactory prediction performance of the model caused by unreasonable selection of trade-off parameters of the loss function. The effectiveness of the TECGC model is evaluated using the PHM2010 dataset. The results demonstrate its capability to accurately predict tool RUL and tool wear stages.

A Common Knowledge-Driven Generic Vision Inspection Framework for Adaptation to Multiple Scenarios, Tasks, and Objects.

The industrial manufacturing model is undergoing a transformation from a product-centric model to a customer-centric one. Driven by customized requirements, the complexity of products and the requirements for quality have increased, which pose a challenge to the applicability of traditional machine vision technology. Extensive research demonstrates the effectiveness of AI-based learning and image processing on specific objects or tasks, but few publications focus on the composite task of the integrated product, the traceability and improvability of methods, as well as the extraction and communication of knowledge between different scenarios or tasks. To address this problem, this paper proposes a common, knowledge-driven, generic vision inspection framework, targeted for standardizing product inspection into a process of information decoupling and adaptive metrics. Task-related object perception is planned into a multi-granularity and multi-pattern progressive alignment based on industry knowledge and structured tasks. Inspection is abstracted as a reconfigurable process of multi-sub-pattern space combination mapping and difference metric under appropriate high-level strategies and experiences. Finally, strategies for knowledge improvement and accumulation based on historical data are presented. The experiment demonstrates the process of generating a detection pipeline for complex products and continuously improving it through failure tracing and knowledge improvement. Compared to the (1.767°, 69.802 mm) and 0.883 obtained by state-of-the-art deep learning methods, the generated pipeline achieves a pose estimation ranging from (2.771°, 153.584 mm) to (1.034°, 52.308 mm) and a detection rate ranging from 0.462 to 0.927. Through verification of other imaging methods and industrial tasks, we prove that the key to adaptability lies in the mining of inherent commonalities of knowledge, multi-dimensional accumulation, and reapplication.

Deep Residual Learning-Based Classification with Identification of Incorrect Predictions and Quantification of Cellularity and Nuclear Morphological Features in Digital Pathological Images of Common Astrocytic Tumors.

Interobserver variations in the pathology of common astrocytic tumors impact diagnosis and subsequent treatment decisions. This study leveraged a residual neural network-50 (ResNet-50) in digital pathological images of diffuse astrocytoma, anaplastic astrocytoma, and glioblastoma to recognize characteristic pathological features and perform classification at the patch and case levels with identification of incorrect predictions. In addition, cellularity and nuclear morphological features, including axis ratio, circularity, entropy, area, irregularity, and perimeter, were quantified via a hybrid task cascade (HTC) framework and compared between different characteristic pathological features with importance weighting. A total of 95 cases, including 15 cases of diffuse astrocytoma, 11 cases of anaplastic astrocytoma, and 69 cases of glioblastoma, were collected in Taiwan Hualien Tzu Chi Hospital from January 2000 to December 2021. The results revealed that an optimized ResNet-50 model could recognize characteristic pathological features at the patch level and assist in diagnosis at the case level with accuracies of 0.916 and 0.846, respectively. Incorrect predictions were mainly due to indistinguishable morphologic overlap between anaplastic astrocytoma and glioblastoma tumor cell area, zones of scant vascular lumen with compact endothelial cells in the glioblastoma microvascular proliferation area mimicking the glioblastoma tumor cell area, and certain regions in diffuse astrocytoma with too low cellularity being misrecognized as the glioblastoma necrosis area. Significant differences were observed in cellularity and each nuclear morphological feature among different characteristic pathological features. Furthermore, using the extreme gradient boosting (XGBoost) algorithm, we found that entropy was the most important feature for classification, followed by cellularity, area, circularity, axis ratio, perimeter, and irregularity. Identifying incorrect predictions provided valuable feedback to machine learning design to further enhance accuracy and reduce errors in classification. Moreover, quantifying cellularity and nuclear morphological features with importance weighting provided the basis for developing an innovative scoring system to achieve objective classification and precision diagnosis among common astrocytic tumors.

Aggressiveness, inhibitory control, and emotional states: A provocation paradigm.

The current study examines the effects of trait aggressiveness, inhibitory control and emotional states on aggressive behavior in a laboratory paradigm. One hundred and fifty-one adult participants took part (73 men, 71 women, and 7 nondisclosed). Event Related Potentials (ERPs) during a Go/No-Go task were utilized to capture the extent of inhibitory processing, with a laboratory provocation paradigm used to assess aggression. Contrary to the expectations, negative affective responses to provocation were negatively associated only with short-lived aggression and only among those with high past aggressiveness. Furthermore, past aggressiveness was related to a continuous increase in laboratory aggressive behavior regardless of the level of inhibitory control (P3 difference amplitude). However, feeling hostile was associated with short-lived aggressive behavior, only in those with lower levels of inhibitory control. These findings demonstrate the effect of distinct mechanisms on different patterns of aggressive behavior.