Limited Feedback Research Articles

Integrating Sparse Reward Handling, Ethical Considerations, And Domain-Specific Adaptation In RlBased Machine Translation For Low-Resource Languages

Effective communication across languages remains a critical challenge, particularly in low-resource settings where conventional machine translation approaches falter due to sparse data and limited quality feedback. This paper presents a holistic framework to enhance reinforcement learning (RL) based machine translation systems tailored for such environments. We address the trifecta of challenges: sparse feedback on translation quality, ethical implications in algorithmic decision-making, and the imperative to adapt models to nuanced linguistic domains. This approach integrates advanced techniques in sparse reward handling, ensuring RL models learn efficiently despite limited feedback. Ethical considerations drive our methodology, emphasizing fairness, bias mitigation, and cultural sensitivity to uphold ethical standards in AI-driven translations. Additionally, domain-specific adaptation strategies are explored to tailor models to diverse linguistic contexts, from technical jargon to colloquialisms, enhancing translation accuracy and relevance. Through a rigorous experimental framework, including evaluation metrics like BLEU score and user feedback, we demonstrate substantial improvements in translation quality and ethical compliance compared to traditional methods. This research contributes to the evolution of robust, inclusive translation technologies pivotal for fostering global understanding and equitable access to information. This paper not only addresses current challenges but also sets a precedent for future research in AI ethics and machine learning applications, advocating for responsible innovation in crosscultural communication technologies

Implementation strategy of insulin therapy under sparse state feedback

Traditional continuous glucose monitoring is often costly and inconvenient, necessitating more efficient methods. This paper proposes a novel approach to diabetes management by utilizing sparse monitoring data for insulin injection decisions. A differential equation-based model is developed to estimate plasma glucose levels and optimize insulin dosages and injection intervals using limited feedback data. This method ensures that glucose levels remain within a safe range. Numerical simulations demonstrate the effectiveness of this approach, offering a viable alternative for improving diabetes management.

The Effect of Guided Conversation Method Toward Students’ Speaking Ability in Eleventh-Grade of MAN 2 Bukittinggi

This study aims to investigate the effect of using the guided conversation method on the speaking ability of eleventh-grade students at MAN 2 Bukittinggi. The research was motivated by the observation that students' speaking scores were below the standard, and teaching methods tended to emphasize memorization. Additionally, students struggled with speaking in English and received limited feedback on their performance. This quasi-experimental research involved pre-tests and post-tests with an experimental and control group. The sample consisted of 58 students selected through cluster random sampling, divided equally into two classes. A speaking test was used as the research instrument, and inter-rater reliability was applied to ensure test consistency. Data analysis included normality and homogeneity tests, while hypothesis testing employed paired sample T-tests and independent sample T-tests using SPSS. The results showed a significant improvement in the speaking ability of students taught using the guided conversation method (Sig. < 0.05). Moreover, a comparison between the experimental and control groups revealed a significant difference, with the experimental group achieving higher post-test scores. Thus, it can be concluded that the guided conversation method effectively improves students' speaking ability.

Enhancing Radiology Training with GPT-4: Pilot Analysis of Automated Feedback in Trainee Preliminary Reports

Rationale and ObjectivesRadiology residents often receive limited feedback on preliminary reports issued during independent call. This study aimed to determine if Large Language Models (LLMs) can supplement traditional feedback by identifying missed diagnoses in radiology residents’ preliminary reports. Materials & MethodsA randomly selected subset of 500 (250 train/250 validation) paired preliminary and final reports between 12/17/2022 and 5/22/2023 were extracted and de-identified from our institutional database. The prompts and report text were input into the GPT-4 language model via the GPT-4 API (gpt-4-0314 model version). Iterative prompt tuning was used on a subset of the training/validation sets to direct the model to identify important findings in the final report that were absent in preliminary reports. For testing, a subset of 10 reports with confirmed diagnostic errors were randomly selected. Fourteen residents with on-call experience assessed the LLM-generated discrepancies and completed a survey on their experience using a 5-point Likert scale. ResultsThe model identified 24 unique missed diagnoses across 10 test reports with i% model prediction accuracy as rated by 14 residents. Five additional diagnoses were identified by users, resulting in a model sensitivity of 79.2%. Post-evaluation surveys showed a mean satisfaction rating of 3.50 and perceived accuracy rating of 3.64 out of 5 for LLM-generated feedback. Most respondents (71.4%) favored a combination of LLM-generated and traditional feedback. ConclusionThis pilot study on the use of LLM-generated feedback for radiology resident preliminary reports demonstrated notable accuracy in identifying missed diagnoses and was positively received, highlighting LLMs' potential role in supplementing conventional feedback methods.

Interim Phase II Results Using Panitumumab-IRDye800CW during Transoral Robotic Surgery in Patients with Oropharyngeal Cancer.

The incidence of oropharyngeal squamous cell carcinoma (OPSCC) has continually increased during the past several decades. Using transoral robotic surgery (TORS) significantly improves functional outcomes relative to open surgery for OPSCC. However, TORS limits tactile feedback, which is often the most important element of cancer surgery. Fluorescence-guided surgery (FGS) strategies to aid surgeon assessment of malignancy for resection are in various phases of clinical research but exhibit the greatest potential impact for improving patient care when the surgeon receives limited tactile feedback, such as during TORS. Here, we assessed the feasibility of intraoperative fluorescence imaging using panitumumab-IRDye800CW (PAN800) during TORS in patients with OPSCC. Twelve consecutive patients with OPSCC were enrolled as part of a nonrandomized, prospective, phase II FGS clinical trial using PAN800. TORS was performed with an integrated robot camera for surgeon assessment of fluorescence. Intraoperative and ex vivo fluorescence signals in tumors and normal tissue were quantified and correlated with histopathology. Intraoperative robot fluorescence views delineated OPSCC from normal tissue throughout the TORS procedure (10.7 mean tumor-to-background ratio), including in tumors with low expression of the molecular target. Tumor-specific fluorescence was consistent with surgeon-defined tumor borders requiring resection. Intraoperative robot fluorescence imaging revealed an OPSCC fragment initially overlooked during TORS based on brightfield views, further substantiating the clinical benefit of this FGS approach. The results from this patient with OPSCC cohort support further clinical assessment of FGS during TORS to aid resection of solid tumors.

Intelligent assistance system for people with visual impairments

Subject of the Research: The creation of an intelligent assistance system for people with visual impairments. Nowadays, the task of developing effective intelligent assistance systems that allow people with vision problems to achieve maximum independence is important and relevant, as existing systems have a number of drawbacks, such as limited autonomy, limited integration with other devices and systems, limited analysis of dynamic obstacles, and limited user feedback capabilities, which in most cases are restricted to voice guidance. Objective: The objective of this work is to create a generalized functional model of an intelligent assistance system for people with visual impairments, which has enhanced autonomy, integration with other devices and systems, the ability to analyze dynamic objects and predict their movement trajectory, and provide diverse feedback to the user. Tasks: To achieve the set objective, the following tasks were accomplished: a generalized functional model of the proposed intelligent assistance system for people with visual impairments was created; the functional dependencies of the components of the developed model were substantiated; a review of the basic modules of the proposed system model was conducted. Methods: The methods used include functional modeling methods and system analysis methods. Results: The following results were obtained: a functional model of an intelligent assistance system for people with visual impairments was proposed. This system surpasses existing analogs in a number of functional capabilities: detection of static and dynamic obstacles with prediction of dynamic obstacles’ movement trajectory, the ability to operate in various conditions (indoors, outdoors, in light or dark, in different weather conditions), support for integration with other systems and devices, and a high level of autonomy. Conclusions: The developed system model has enhanced autonomy, integration with other devices and systems, the ability to analyze dynamic objects and predict their movement trajectory, and provides diverse feedback to the user.

How to make recommendations on mobile social e-commerce more effective: The role of social features and temporal cues

This study explores the role of design affordance of social display features in mobile social e-commerce with recommendations. Building upon the intersection of signaling theory and construal level theory, we address two paradoxes regarding social and temporal cues in recommending (close social distance vs. limited feedback and recency vs. magnitude). The results from four experiments indicate that friend-based feedback induces larger purchases than crowd-based feedback. Temporal distance moderates this relationship. Specifically, when temporal cues indicate proximal distance, recommendations from friends (by showing their feedback) are more persuasive than those from crowds. Conversely, the opposite occurs at further temporal distance.

HRM practices in app work: exploring training and feedback in the food delivery ecosystem

Purpose This study aims to explore the human resource management (HRM) practices related to training and feedback in the app work industry, specifically in online food delivery service, and investigate the emotional and behavioral responses of gig workers. Design/methodology/approach This study adopts a qualitative approach by interviewing 19 gig workers from six food delivery firms operating in different countries. Findings The results show limited training and feedback opportunities are provided to app workers, although the complexity of training and delivery methods differ across platforms. To address this shortage, app workers developed response strategies relying on social interaction. Research limitations/implications This study adds to the research on HRM practices in the gig economy by portraying the way in which training and feedback unfold in the food delivery app ecosystem and by disclosing the gig workers’ emotional and behavioral responses to it. Practical implications This study shows that the way training activities are currently designed may provide little value to the ecosystem and are likely to produce negative emotional responses in gig workers. Thus, platform providers may make use of these findings by introducing more transparent feedback and social learning opportunities. Originality/value To the best of the authors’ knowledge, this study is among the first empirical studies on online delivery gig workers addressing specific HRM practices. It reveals significant insights for training and feedback, suggesting app economy characteristics strongly affect training and feedback practices for app workers.

Abstract PO2-10-12: The devil is in the details: Workflow analysis of breast cancer treatment decision making and implications for decision support design

Abstract While numerous decision aids have been developed to support treatment decision-making in breast cancer1, widespread implementation remains limited due to challenges integrating these tools in clinical workflows2. Given these persistent issues, we need to better understand the complex workflows and needs of decision aid users - patients, their family caregivers, and breast cancer clinicians. Previous studies have explored various aspects of breast cancer team workflows3,4. Despite this work, it is still unclear how these complex workflows support or hinder decision aid use. In this study, we conducted an in-depth analysis of breast cancer team workflow to elicit design requirements for informatics tools to support patient-centered decision-making. This study was part of a larger project aimed at designing a COMputeried PAtient-centered Collaborative Technology (COMPACT) to support personalized decision-making for breast cancer patients. We conducted observations of clinicians and patients at one breast center, using a tablet computer with smart pen to take notes on all aspects of clinic workflow. We uploaded all observation notes into a qualitative data analysis software, Dedoose. Two researchers coded the observations in an inductive, consensus-based process. We met to review our codes and identify key themes emerging in the data. We observed 95 hours and 127 patient encounters across 20 clinician-centered and 8 patient-centered observations. We identified 10 themes related to the design of decision support, which we grouped into the 4 components of workflow6 (see Table 1). We identified numerous patient-specific factors communicated from the patient to the clinical team that influenced treatment decision-making. These “decision factors” covered the broader scope of the patient’s life that was important in the decision-making process (e.g., upcoming family wedding, work). Patients were frequently “knowledge brokers” and were asked to remember and relay information across members of the care team. We identified 28 different tools and technologies used to support treatment decision-making. Patient family caregivers (e.g., aunt, husband) played an important role in treatment decision-making. Based on these findings, we developed design requirements for informatics tools to better support patients (and clinicians). Our study highlights the complexity and interdependence of breast cancer treatment decision-making. Patients frequently made treatment decisions that influenced subsequent decisions. Decision aids typically focus on one decision or one care specialty and do not support consideration of several treatment options at one time1. Future research is needed to determine if and how decision support tools could incorporate the broader scope and interdependence between decisions to support patient-centered care. We highlight the need for informatics tools to consider the diverse and unique decision factors (e.g., hobbies) that are crucial to patient-centered decision-making. Decision support could help to elicit and incorporate these factors during treatment decision-making. However, the variable nature of these patient-specific factors presents a challenge to decision support design. Further research is needed to determine how to optimally incorporate such factors into decision support tools. We found inadequate system support for clinicians’ tasks including limited feedback loops to notify clinicians of completed tasks (e.g., mammogram, genetic testing). As a result, patients were often responsible for relaying information to and between different members of the clinical team. Given that patients only remember 50% of what clinicians tell them during visits7, a better system is needed to improve the reliability of information transfer. Our design guidelines can be used to improve the design of decision support tools and ultimately improve patient-centered decision-making. Table 1. Workflow components, themes, and associated challenges to decision support design Citation Format: Megan Salwei, Carrie Reale. The devil is in the details: Workflow analysis of breast cancer treatment decision making and implications for decision support design [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-10-12.

Considering the Development and Evaluation of Engineers as Teachers

Engineering faculty are required to teach but are rarely trained in evidence-based practices in teaching and learning. While many faculty often mirror how they were taught and slowly develop their curriculum and skills over time, the methods for their development cannot keep pace with the rapidly changing landscape of engineering classrooms. This includes changes in students’ needs, pedagogical advances, and the technology accessible to students. In response to the need for training, development, and continuous improvement of engineering faculty’s teaching beyond the limited feedback that student and peer evaluations provide, our department piloted a program offering 18 different options for teaching development activities. Faculty could choose from these options to enhance their teaching practices. Three focus groups were conducted with a total of 12 faculty participants to iterate and improve upon the piloted program. Qualitative analysis of these focus groups, involving multiple phases of coding and general theming of the focus group transcript data, revealed more than just the faculty’s impressions of the piloted program. Our analysis revealed that two value systems exist when it comes to teaching and teaching development: what is valued personally by a faculty member and what is valued systemically by the department, college, university, or field they work within. The identification of these two distinct value systems revealed that misalignments exist between them. What faculty personally value about their teaching and teaching development might not be valued by the systems in place, and vice versa. We present examples of how faculty discuss these two value systems and explore the implications of conflicting value systems, as well as opportunities for departments to enhance alignment between these value systems to boost faculty motivation for regular engagement with teaching development practices.

Potential-based reward shaping using state–space segmentation for efficiency in reinforcement learning

Reinforcement Learning (RL) algorithms encounter slow learning in environments with sparse explicit reward structures due to the limited feedback available on the agent’s behavior. This problem is exacerbated particularly in complex tasks with large state and action spaces. To address this inefficiency, in this paper, we propose a novel approach based on potential-based reward-shaping using state–space segmentation to decompose the task and to provide more frequent feedback to the agent. Our approach involves extracting state–space segments by formulating the problem as a minimum cut problem on a transition graph, constructed using the agent’s experiences during interactions with the environment via the Extended Segmented Q-Cut algorithm. Subsequently, these segments are leveraged in the agent’s learning process through potential-based reward shaping. Our experimentation on benchmark problem domains with sparse rewards demonstrated that our proposed method effectively accelerates the agent’s learning without compromising computation time while upholding the policy invariance principle.

How spotting technique affects dizziness and postural stability after full-body rotations in dancers

Consecutive longitudinal axis rotations are very common in dance, ranging from head spins in break dance to pirouettes in ballet. They pose a rather formidable perceptuomotor challenge – and hence form an interesting window into human motor behaviour – yet they have been scarcely studied. In the present study, we investigated dancers' dizziness and postural stability after consecutive rotations. Rotations were performed actively or undergone passively, either with or without the use of a spotting technique in such an order that all 24 ordering options were offered at least once and not more than twice.Thirty-four dancers trained in ballet and/or contemporary dance (aged 27.2 ± 5.1 years) with a mean dance experience of 14.2 ± 7.1 years actively performed 14 revolutions in passé or coupé positions with a short gesture leg “foot down” after each revolution. In addition, they were passively turned through 14 revolutions on a motor-driven rotating chair. Participants' centre-of-pressure (COP) displacement was measured on a force-plate before and after the rotations. Moreover, the dancers indicated their subjective feeling of dizziness on a scale from 0 to 20 directly after the rotations. Both the active and passive conditions were completed with and without the dancers spotting.As expected, dizziness was worse after rotations without the adoption of the spotting technique, both in active and passive rotations. However, the pre-post difference in COP area after active rotations was unaffected by spotting, whereas in the passive condition, spotting diminished this difference. Our results thus suggest that adopting the spotting technique is a useful tool for dizziness reduction in dancers who have to perform multiple rotations. Moreover, spotting appears most beneficial for postural stability when it involves less postural control challenges, such as when seated on a chair and occurs in situations with limited somatosensory feedback (e.g., from the cutaneous receptors in the feet). However, the unexpected finding that spotting did not help postural stability after active rotations needs to be investigated further in future studies, for example with a detailed analysis of whole-body kinematics and eye-tracking.

Perception and Action Augmentation for Teleoperation Assistance in Freeform Telemanipulation

Teleoperation enables controlling complex robot systems remotely, providing the ability to impart human expertise from a distance. However, these interfaces can be complicated to use as it is difficult to contextualize information about robot motion in the workspace from the limited camera feedback. Thus, it is required to study the best manner in which assistance can be provided to the operator that reduces interface complexity and effort required for teleoperation. Some techniques that provide assistance to the operator while freeform teleoperating include: (1) perception augmentation, like augmented reality visual cues and additional camera angles, increasing the information available to the operator; (2) action augmentation, like assistive autonomy and control augmentation, optimized to reduce the effort required by the operator while teleoperating. In this article, we investigate: (1) which aspects of dexterous telemanipulation require assistance; (2) the impact of perception and action augmentation in improving teleoperation performance; and (3) what factors impact the usage of assistance and how to tailor these interfaces based on the operators’ needs and characteristics. The findings from this user study and resulting post-study surveys will help identify task-based and user-preferred perception and augmentation features for teleoperation assistance.

Investigation of policy tools for energy efficiency improvement in public buildings in China—current situation, obstacles, and solutions

The energy consumption from the building sector accounts for more than 21% of the total in China, where the energy-use intensity of public buildings could reach 3 times that of residential buildings. Energy efficiency improvement (EEI) is considered to be one of the most rapid and cost-effective means for the building sector to achieve carbon neutrality. The Chinese government has carried out a series of policy tool exploration to promote the energy efficiency improvement efforts by public building owners since over a decade ago, but encountered various problems and obstacles. This paper investigated and compared the current status challenges, and problems in the implementation of EEI policy tools in China and developed countries through literature review, field investigations and interviews with experts and stakeholders, and finally also put forward some possible coping strategies for Chinese government. Results indicated that energy grading and labeling, energy benchmarking, carbon-emission trading and energy-consumption quota management were the main 4 EEI policy tools designed based on measured energy consumption data, where the first 3 ones had been widely used over the developed countries but the last one was unique to China. Difficulty in large-scale collection of building energy-consumption data, lack of scientific methods on building energy-use level evaluation, limited data application and feedback, undesirable association between stakeholders, etc., were the main obstacles for achieving the long-term effectiveness of the EEI policy tools. Cooperating with energy supply enterprises to collect data, establishing an effective energy grading system and a closed loop of policy implementation, exploring a new model of building carbon-emission trading and a differential pricing mechanism, combined with innovative financial supports, might be the solutions. The main contribution of this study is that a comprehensive investigation and analysis on the current development status, obstacles, and possible solutions of the public building EEI policy tools in China was carried out, which is expected to provide a reference for the government of China and even the world.

Virtual Reality‐Enabled Intuitive Magnetic Manipulation of Microrobots and Nanoparticles

Magnetic microrobots and nanoparticles offer unique capabilities for medical applications by granting unprecedented access to intricate and delicate anatomical structures. Nevertheless, an intuitive manipulation approach remains a challenge due to their small size and limited feedback. This study presents a new method for magnetic microrobot and nanoparticle control that employs virtual reality (VR), creating an immersive and realistic view of the bodily anatomy and the microrobot within. This study compares three manipulation modes: a traditional mode using 2D displays, VR mode using a VR headset and touch controllers, and VR autonomous programmed maneuvering. It is shown that VR‐assisted modes reduce the manipulation time by improving spatial awareness. Nanoparticles in a VR environment are also manipulated. The proposed method will find applications in terms of intuitive, immersive microrobots or magnetic nanoparticle control in complex biological environments, thus in many medical procedures and for drug and cell delivery. The immersive nature of this approach enhances the ability of the user to perceive and understand complex anatomical structures, facilitating better navigation within delicate environments; both dexterity and spatial awareness are improved. Thus, it is shown how microrobots and magnetic nanoparticles can be controlled using immersive simulations to improve both visualization and manipulation.

Generalizable Black-Box Adversarial Attack With Meta Learning.

In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget. Due to the limited feedback information, existing query-based black-box attack methods often require many queries for attacking each benign example. To reduce query cost, we propose to utilize the feedback information across historical attacks, dubbed example-level adversarial transferability. Specifically, by treating the attack on each benign example as one task, we develop a meta-learning framework by training a meta generator to produce perturbations conditioned on benign examples. When attacking a new benign example, the meta generator can be quickly fine-tuned based on the feedback information of the new task as well as a few historical attacks to produce effective perturbations. Moreover, since the meta-train procedure consumes many queries to learn a generalizable generator, we utilize model-level adversarial transferability to train the meta generator on a white-box surrogate model, then transfer it to help the attack against the target model. The proposed framework with the two types of adversarial transferability can be naturally combined with any off-the-shelf query-based attack methods to boost their performance, which is verified by extensive experiments. The source code is available at https://github.com/SCLBD/MCG-Blackbox.

“Doing well”: Intraoperative entrustable professional activity assessments provided limited technical feedback

BackgroundEntrustable Professional Activities (EPAs) allow for the assessment of specific, observable, essential tasks in medical education. Since being developed in non-surgical fields, EPA assessments have been implemented in surgery to explore intraoperative entrustment. However, assessment burden is a significant problem for faculty, and it is unknown whether EPA assessments enable formative technical feedback. EPAs' formative utility could inform how surgical programs facilitate technical feedback for trainees. We aimed to assess the extent to which narrative comments provided through the Fellowship Council (FC) EPA assessments contained technical feedback. MethodsThe FC previously collected EPA assessments for subspecialty surgical fellows from September 2020 to October 2022. Two raters reviewed assessments' narrative comments for inclusion of each skill area that makes up part of the Objective Structured Assessment of Technical Skills (OSATS). A third rater reconciled discrepant ratings. ResultsDuring the study period, there were 3302 completed EPA assessments, including 1191 fellow self-assessments, 1124 faculty assessments, and 987 assessments without an identified assessor role. We found that assessments' narrative comments related to a median of two of the seven OSATS areas (IQR:1–2). There were no comments relevant to any of the seven OSATS areas in 16.0 % of all assessments. ConclusionsIn this review of narrative comments for EPA assessments from the FC, we found that limited technical feedback of the kind included in the OSATS was provided in many assessments. These results suggest benefit to adjusting the EPA form, enhancing faculty development, or continuing additional types of targeted technical assessment intraoperatively. Key messageThis analysis of narrative comments from fellowship EPA assessments showed that many assessments included limited technical feedback. To allow for continued technical feedback for fellows, these results highlight the need for further refinements of the EPA assessment form, additional faculty development, or ongoing use of other types of technical assessment.

Comparing eye-hand coordination between controller-mediated virtual reality, and a real-world object interaction task.

Virtual reality (VR) technology has advanced significantly in recent years, with many potential applications. However, it is unclear how well VR simulations mimic real-world experiences, particularly in terms of eye-hand coordination. This study compares eye-hand coordination from a previously validated real-world object interaction task to the same task re-created in controller-mediated VR. We recorded eye and body movements and segmented participants' gaze data using the movement data. In the real-world condition, participants wore a head-mounted eye tracker and motion capture markers and moved a pasta box into and out of a set of shelves. In the VR condition, participants wore a VR headset and moved a virtual box using handheld controllers. Unsurprisingly, VR participants took longer to complete the task. Before picking up or dropping off the box, participants in the real world visually fixated the box about half a second before their hand arrived at the area of action. This 500-ms minimum fixation time before the hand arrived was preserved in VR. Real-world participants disengaged their eyes from the box almost immediately after their hand initiated or terminated the interaction, but VR participants stayed fixated on the box for much longer after it was picked up or dropped off. We speculate that the limited haptic feedback during object interactions in VR forces users to maintain visual fixation on objects longer than in the real world, altering eye-hand coordination. These findings suggest that current VR technology does not replicate real-world experience in terms of eye-hand coordination.

Controlling Musculoskeletal System with Spinal Cord-Inspired Constraint Force Field Primitives

Organisms naturally have extraordinary motor ability. They can autonomously control the highly redundant and nonlinear musculoskeletal system to complete fast and flexible movements. Motor primitive theory proposed that a complex movement can be realized by modular organization of simple movement patterns. This theory provides a convincing theoretical basis for explaining the extraordinary motor ability of organisms, and has been supported by plenty of experimental evidences in neurosciences. As a kind of typical motor primitive related to the modular regulation of the spinal motor system, convergent force field was thought to be significant for reducing the complexity of controlling numerous muscles and joints simultaneously. Inspired by the primitive property of convergent force field, in this paper, we proposed a new algorithm to efficiently construct constraint force field on musculoskeletal system with highly redundant actuators by taking optimized parameters of constraint force field as motor primitives. Compared with previous methods of constructing constraint force field, the proposed algorithm is able to reduce the dimension of the solution space so as to effectively improve the computational efficiency of constructing constraint force field in musculoskeletal system with redundant muscles. Validation experiments were carried out in a musculoskeletal system with 10 redundant muscles. The number of optimization iterations and computational time required for constructing constraint force field at a new position were significantly reduced. The system can accurately reach the target position using constant activations. This work may bring in new inspiration for realizing efficient and accurate motion control of musculoskeletal robots with limited feedback accuracy.

Micromanagement and its impact on millennial followership styles

PurposeIt is predicted that micromanagement may become a growing workplace concern post-Covid-19, with managers grappling for control in the current hybrid/remote working environment. This will be happening at a time when millennials represent half of the working population. This study contributes to existing literature and provides an overall appreciation of the complexities of micromanagement and how it impacts millennials' followership styles.Design/methodology/approachA quantitative study was undertaken and a series of hypotheses were tested. The target sample for this research was the millennial cohort aged between 24 and 41. Data were analysed using SPSS.FindingsThis paper confirmed that “unfavourable followership styles” consisted of various negative followership reactions such as anxiety, demotivation, dissatisfaction, disengagement, reduction in support for managers, limited upward feedback, team conflict, reduced productivity and innovation due to fear of making mistakes ultimately facilitating a toxic workplace. Essentially, this research validated the notion that in order to create a sustainable organisation post-Covid-19, HR professionals must take proactive measures to mitigate this form of harmful leadership.Research limitations/implicationsData weaknesses transpire where respondents have never interacted with a micromanager in reality. Therefore, perceived reactions to a hypothetical micromanager may differ from those respondents who were exposed to micromanagers.Originality/valueA lack of research exists on the intersection of micromanagement and millennials' followership styles and as such this paper bridges that gap.