Task-oriented Manner Research Articles

AN INTERNATIONAL PERSPECTIVE ON OPTIMIZING FUNCTION AND ACTIVITY IN GERIATRIC CLIENTS ACROSS ALL SITES OF CARE

Abstract With an increasing age, people are at risk for functional decline and care dependency. Frail older people in any site of care –at home, in nursing homes and in acute care– are supported by nursing staff to optimize their functioning, remain active, and maximize their independence. However, nursing staff often tend to work in a task-oriented manner and take over tasks unnecessarily which may deprive older people’s remaining abilities and adversely impact their life quality. Nursing staff require support to improve their activity supportive behavior in practice. This symposium presents the results of several international studies from primary care, home care, nursing home care and acute care, which aim to improve nursing staff behavior and –in turn– client outcomes. First, Prof. Galik will present the results of a randomized controlled theoretically-based trial testing the ‘Function-Focused Care’ approach in which over 350 patients participated. Dr. Vluggen will present the results of a cluster-randomized trial conducted in Dutch nursing home care in which the effectiveness of the ‘SELF-program’ is evaluated, including over 250 nursing staff and 200 patients. Dr. Metzelthin will discuss the feasibility of the SELF-program, which has been subjected to a thorough pilot-study in Dutch home care. Last, Prof. Graff will discuss the experiences of people with dementia and caregivers after following a coaching-based psychosocial program for primary care (SOCAV). The symposium is chaired by Dr. Vluggen and discussed by Prof. Resnick who has a considerable track record in intervention studies focusing on optimizing function and activity in geriatric clients.

Multi-Constraint Latent Representation Learning for Prognosis Analysis Using Multi-Modal Data.

The Cox proportional hazard model has been widely applied to cancer prognosis prediction. Nowadays, multi-modal data, such as histopathological images and gene data, have advanced this field by providing histologic phenotype and genotype information. However, how to efficiently fuse and select the complementary information of high-dimensional multi-modal data remains challenging for Cox model, as it generally does not equip with feature fusion/selection mechanism. Many previous studies typically perform feature fusion/selection in the original feature space before Cox modeling. Alternatively, learning a latent shared feature space that is tailored for Cox model and simultaneously keeps sparsity is desirable. In addition, existing Cox-based models commonly pay little attention to the actual length of the observed time that may help to boost the model's performance. In this article, we propose a novel Cox-driven multi-constraint latent representation learning framework for prognosis analysis with multi-modal data. Specifically, for efficient feature fusion, a multi-modal latent space is learned via a bi-mapping approach under ranking and regression constraints. The ranking constraint utilizes the log-partial likelihood of Cox model to induce learning discriminative representations in a task-oriented manner. Meanwhile, the representations also benefit from regression constraint, which imposes the supervision of specific survival time on representation learning. To improve generalization and alleviate overfitting, we further introduce similarity and sparsity constraints to encourage extra consistency and sparseness. Extensive experiments on three datasets acquired from The Cancer Genome Atlas (TCGA) demonstrate that the proposed method is superior to state-of-the-art Cox-based models.

Task-Oriented Grasping Position Selection in Deformable Object Manipulation

Grasping mechanisms in robotic deformable object manipulation (DOM) remain under-investigated due to the intrinsic complexity of DOM. For grasping in DOM, grasping position selection is crucial since external forces are applied to grasping locations on the deformable object (DO) to make it deform. The feasibility and efficiency of performing a specific DOM task thus highly depend on where grasps are placed. This letter investigates the grasping position selection problem in DOM. In particular, we tackle it in a task-oriented manner to facilitate robot deforming operations. For common deformation description methods (image feature and point cloud) and grasping scenarios (single and dual grasps), we develop grasping position selection methods that take into account the properties of both the task and DO. Specifically, metrics are first constructed to quantify grasping position quality when conducting the deforming process. Algorithms are then proposed based on metrics, which enable robots to select appropriate grasping positions in DOM. We evaluated our methods in both simulations and hardware experiments.

Task-Oriented Communication for Multidevice Cooperative Edge Inference

This paper investigates task-oriented communication for multi-device cooperative edge inference, where a group of distributed low-end edge devices transmit the extracted features of local samples to a powerful edge server for inference. While cooperative edge inference can overcome the limited sensing capability of a single device, it substantially increases the communication overhead and may incur excessive latency. To enable low-latency cooperative inference, we propose a learning-based communication scheme that optimizes local feature extraction and distributed feature encoding in a task-oriented manner, i.e., to remove data redundancy and transmit information that is essential for the downstream inference task rather than reconstructing the data samples at the edge server. Specifically, we leverage Tishby’s information bottleneck (IB) principle (Tishby et al., 2000) to extract the task-relevant feature at each edge device, and adopt the distributed information bottleneck (DIB) framework of Aguerri and Zaidi, 2021, to formalize a single-letter characterization of the optimal rate-relevance tradeoff for distributed feature encoding. To admit flexible control of the communication overhead, we extend the DIB framework to a distributed deterministic information bottleneck (DDIB) objective that explicitly incorporates the representational costs of the encoded features. As the IB-based objectives are computationally prohibitive for high-dimensional data, we adopt variational approximations to make the optimization problems tractable. To compensate for the potential performance loss due to the variational approximations, we also develop a selective retransmission (SR) mechanism to identify the redundancy in the encoded features among multiple edge devices to attain additional communication overhead reduction. Extensive experiments on multi-view image classification and multi-view object recognition tasks evidence that the proposed task-oriented communication scheme achieves a better rate-relevance tradeoff than existing methods.

Toward Ambient Intelligence: Federated Edge Learning With Task-Oriented Sensing, Computation, and Communication Integration

With the breakthroughs in deep learning and contactless sensors, the recent years have witnessed a rise of ambient intelligence applications and services, spanning from healthcare delivery to intelligent home. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Federated edge learning</i> (FEEL), as a privacy-enhancing paradigm of collaborative learning at the network edge, is expected to be the core engine to achieve ambient intelligence. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sensing, computation, and communication</i> (SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> ) are highly coupled processes in FEEL and need to be jointly designed in a task-oriented manner to achieve the best FEEL performance under stringent resource constraints at edge devices. However, this remains an open problem as there is a lack of theoretical understanding on how the SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> resources jointly affect the FEEL performance. In this paper, we address the problem of joint SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> resource allocation for FEEL via a concrete case study of human motion recognition based on wireless sensing in ambient intelligence. First, by analyzing the wireless sensing process in human motion recognition, we find that there exists a thresholding value for the sensing transmit power, exceeding which yields sensing data samples with approximately the same satisfactory quality. Then, the joint SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> resource allocation problem is cast to maximize the convergence speed of FEEL, under the constraints on training time, energy supply, and sensing quality of each edge device. Solving this problem entails solving two subproblems in order: the first one reduces to determine the joint sensing and communication resource allocation that maximizes the total number of samples that can be sensed during the entire training process; the second one concerns the partition of the attained total number of sensed samples over all the communication rounds to determine the batch size at each round for convergence speed maximization. The first subproblem on joint sensing and communication resource allocation is converted to a single-variable optimization problem by exploiting the derived relation between different control variables (resources), which thus allows an efficient solution via one-dimensional grid search. For the second subproblem, it is found that the number of samples to be sensed (or batch size) at each round is a decreasing function of the loss function value attained at the round. Based on this relationship, the approximate optimal batch size at each communication round is derived in closed-form as a function of the round index. Finally, extensive simulation results are provided to validate the superiority of the proposed joint SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> resource allocation scheme over baseline schemes in terms of FEEL performance.

Effect, economic and process-evaluation of a generic function focused care program for long-term care; study protocol of a multicenter cluster–randomized trial

BackgroundNurses are in a key position to stimulate older people to maximize their functional activity and independence. However, nurses still often work in a task-oriented manner and tend to take over tasks unnecessarily. It is evident to support nurses to focus on the capabilities of older people and provide care assistance only when required. Function-Focused Care (FFC) is a holistic care-philosophy aiming to support nurses to deliver care in which functioning and independence of older people is optimized. Dutch and internationally developed FFC-based interventions often lack effectiveness in changing nurses’ and client’s behavior. Process-evaluations have yielded lessons and implications resulting in the development of an advanced generic FFC-program: the ‘SELF-program’. The SELF-program aims to improve activity stimulation behavior of nurses in long-term care services, and with that optimize levels of self-reliance in activities of daily living (ADL) in geriatric clients. The innovative character of the SELF-program lies for example in the application of extended behavior change theory, its interactive nature, and tailoring its components to setting-specific elements and needs of its participants. This paper describes the outline, content and theoretical background of the SELF-program. Subsequently, this paper describes a protocol for the assessment of the program’s effect, economic and process-evaluation in a two-arm (SELF-program vs care as usual) multicenter cluster-randomized trial (CRT).MethodThe proposed CRT has three objectives, including getting insight into the program’s: (1) effectiveness regarding activity stimulation behavior of nurses and self-reliance in ADL of geriatric clients, and (2) cost-effectiveness from a societal perspective including assessments of quality of life and health-care use. Measurements will take place prior to program implementation (baseline), directly after (T1), and in long-term (T2). Parallel to the CRT, a process evaluation will be conducted to provide insight into the program’s: (3) feasibility regarding implementation, mechanisms of impact and contextual factors.DiscussionThe SELF-program was developed following the Medical Research Council framework, which addresses the systematic development, feasibility testing, evaluation and implementation of complex interventions. The program has been subjected to a feasibility study before and results of studies described in this protocol are expected to be available from end 2022 onwards.Trial-registrationThe study is registered in the Dutch Trial Register (NL9189), as of December 22 2020.

Explanation-Aware Experience Replay in Rule-Dense Environments

Human environments are often regulated by explicit and complex rulesets. Integrating Reinforcement Learning (RL) agents into such environments motivates the development of learning mechanisms that perform well in rule-dense and exception-ridden environments such as autonomous driving on regulated roads. In this paper, we propose a method for organising experience by means of partitioning the experience buffer into clusters labelled on a per-explanation basis. We present discrete and continuous navigation environments compatible with modular rulesets and 9 learning tasks. For environments with explainable rulesets, we convert rule-based explanations into case-based explanations by allocating state-transitions into clusters labelled with explanations. This allows us to sample experiences in a curricular and task-oriented manner, focusing on the rarity, importance, and meaning of events. We label this concept Explanation-Awareness (XA). We perform XA experience replay (XAER) with intra and inter-cluster prioritisation, and introduce XA-compatible versions of DQN, TD3, and SAC. Performance is consistently superior with XA versions of those algorithms, compared to traditional Prioritised Experience Replay baselines, indicating that explanation engineering can be used in lieu of reward engineering for environments with explainable features.

Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach

This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data into an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">informative</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">compact</i> representation for low-latency inference given the limited bandwidth. We propose a learning-based communication scheme that jointly optimizes feature extraction, source coding, and channel coding in a task-oriented manner, i.e., targeting the downstream inference task rather than data reconstruction. Specifically, we leverage an information bottleneck (IB) framework to formalize a rate-distortion tradeoff between the informativeness of the encoded feature and the inference performance. As the IB optimization is computationally prohibitive for the high-dimensional data, we adopt a variational approximation, namely the variational information bottleneck (VIB), to build a tractable upper bound. To reduce the communication overhead, we leverage a sparsity-inducing distribution as the variational prior for the VIB framework to sparsify the encoded feature vector. Furthermore, considering dynamic channel conditions in practical communication systems, we propose a variable-length feature encoding scheme based on dynamic neural networks to adaptively adjust the activated dimensions of the encoded feature to different channel conditions. Extensive experiments evidence that the proposed task-oriented communication system achieves a better rate-distortion tradeoff than baseline methods and significantly reduces the feature transmission latency in dynamic channel conditions.

Saliency map-guided hierarchical dense feature aggregation framework for breast lesion classification using ultrasound image

Deep learning methods, especially convolutional neural networks, have advanced the breast lesion classification task using breast ultrasound (BUS) images. However, constructing a highly-accurate classification model still remains challenging due to complex pattern, relatively-low contrast and fuzzy boundary existing between lesion regions (i.e., foreground) and the surrounding tissues (i.e., background). Few studies have separated foreground and background for learning domain-specific representations, and then fused them for improving performance of models. In this paper, we propose a saliency map-guided hierarchical dense feature aggregation framework for breast lesion classification using BUS images. Specifically, we first generate saliency maps for foreground and background via super-pixel clustering and multi-scale region grouping. Then, a triple-branch network, including two feature extraction branches and a feature aggregation branch, is constructed to learn and fuse discriminative representations under the guidance of priors provided by saliency maps. In particular, two feature extraction branches take the original image and corresponding saliency map as input for extracting foreground- and background-specific representations. Subsequently, a hierarchical feature aggregation branch receives and fuses the features from different stages of two feature extraction branches, for lesion classification in a task-oriented manner. The proposed model was evaluated on three datasets using 5-fold cross validation, and experimental results have demonstrated that it outperforms several state-of-the-art deep learning methods on breast lesion diagnosis using BUS images.

Generative domain adaptation for chest X‐ray image analysis

Chest X-ray images taken under different conditions follow different distributions, preventing the models trained on a domain from generalising well on the other domain. In this paper, a generative domain adaptation (GDA) method is proposed to address this issue and facilitate the learning process for downstream analysis. GDA adapts different domains to a virtual common one where images are aligned at the appearance level. To this end, a domain shared generator is used to transform the input images and two competitive discriminators are used to adversarially supervise the transforming process. The domain discriminator drives the generator to narrow the domain gap while the fidelity discriminator forces the generator to keep the inherent information. Moreover, a specific classification or detection network is attached to the generator to supervise it in a task-oriented manner. Experiment results on a large-scale dataset containing 46k chest X-ray images demonstrate that GDA outperforms representative domain adaptation methods by a large margin for both disease classification and lesion detection as well as provides useful transformed images to assist experts for diagnosis.

Identity dimensions versus proactive coping in late adolescence while taking into account biological sex and psychological gender

Abstract The aim of study was to investigate the relationship between proactive coping strategies and the dimensions of identity formation, along with the role of biological sex and psychological gender as moderators for this relationship. We conducted analyses aimed at showing differences in terms of identity dimensions levels and proactive coping strategies used by a group of individuals with different biological sex and psychological gender. A group of 101 students from upper secondary schools (47 females, 54 males) from Pomeranian Voivodeship took part in the study. We used in our research The Dimensions of Identity Development Scale; The Psychological Gender Inventory and The Proactive Coping Inventory for Adolescents. We found, among others, that in the case of a proactive strategy, biological sex turned out to be a significant moderator in the relationship between this variable and identity dimensions: ruminative exploration, commitment-making and identification with commitment. In the case of instrumental support seeking, psychological gender turned out to be a significant moderator for the relationship between these variables and a part of identity dimensions. The obtained results show that, regardless of whether young people, in terms of characteristics that are stereotypically associated with biological sex, are described as aschematic (undifferentiated individuals) or schematic (sex-typed) when entering adulthood and attempting to constitute themselves, more often cope in a task-oriented manner by trying to create a set of information useful in difficult situations and aspire to obtain informational support from individuals in one’s own social network, who are regarded as safe people.

The Body as an Object—a Sociocultural Perspective: The Study of Young Adults’ Narratives

The authors analyse the problem of the objectification of the body, searching for the cultural sources of this phenomenon, and try to outline the consequences of body objectification. When objectified, the body is treated in an instrumental, task-oriented manner, which implies that its value stems from its usefulness in achieving goals. The paper focuses on the ways in which young adults describe their bodies. In the study, responses to the question What does the body mean to you? were collected from 136 young adults. The obtained narratives were examined with the qualitative method of narrative analysis. The results indicate that the objectifying approach to body perception is clearly dominant in the participants’ responses in the following categories: a tool, a connector, a showcase, a machine and an object. The authors discuss some possible ways to change the dominant social metaphors concerning the body.

Task-Based Robot Grasp Planning Using Probabilistic Inference

Grasping and manipulating everyday objects in a goal-directed manner is an important ability of a service robot. The robot needs to reason about task requirements and ground these in the sensorimotor information. Grasping and interaction with objects are challenging in real-world scenarios, where sensorimotor uncertainty is prevalent. This paper presents a probabilistic framework for the representation and modeling of robot-grasping tasks. The framework consists of Gaussian mixture models for generic data discretization, and discrete Bayesian networks for encoding the probabilistic relations among various task-relevant variables, including object and action features as well as task constraints. We evaluate the framework using a grasp database generated in a simulated environment including a human and two robot hand models. The generative modeling approach allows the prediction of grasping tasks given uncertain sensory data, as well as object and grasp selection in a task-oriented manner. Furthermore, the graphical model framework provides insights into dependencies between variables and features relevant for object grasping.

Malnutrition in elder care: qualitative analysis of ethical perceptions of politicians and civil servants

BackgroundFew studies have paid attention to ethical responsibility related to malnutrition in elder care. The aim was to illuminate whether politicians and civil servants reason about malnutrition in elder care in relation to ethical responsibility, and further about possible causes and how to address them.MethodEighteen elected politicians and appointed civil servants at the municipality and county council level from two counties in Sweden were interviewed. They worked at a planning, control and executive level, with responsibility for both the elder care budget and quality of care. Qualitative method was used for the data analysis.ResultsTwo themes emerged from their reasoning about malnutrition related to ethical responsibility. The theme assumed role involves the subthemes quality of care and costs, competent staff and govern at a distance. Old and ill patients were mentioned as being at risk for malnutrition. Caregivers were expected to be knowledgeable and stated primary responsible for providing adequate nutritional care. Extended physician responsibility was requested owing to patients' illnesses. Little was reported on the local management's role or on their own follow-up routines. The theme moral perception includes the subthemes discomfort, trust and distrust. Feelings of discomfort concerned caregivers having to work in a hurried, task-oriented manner. Trust meant that they believed for the most part that caregivers had the competence to deal appropriately with nutritional care, but they felt distrust when nutritional problems reappeared on their agenda. No differences could be seen between the politicians and civil servants.ConclusionNew knowledge about malnutrition in elder care related to ethical responsibility was illuminated by persons holding top positions. Malnutrition was stressed as an important dimension of the elder care quality. Governing at a distance meant having trust in the staff, on the one hand, and discomfort and distrust when confronted with reports of malnutrition, on the other. Distrust was directed at caregivers, because despite the fact that education had been provided, problems reappeared. Discomfort was felt when confronted with examples of poor nutritional care and indicates that the participants experienced failure in their ethical responsibility because the quality of nutritional care was at risk.

Effects of the Space Shuttle Cockpit Avionics Upgrade on Crewmember Performance and Situation Awareness

The Space Shuttle Cockpit Avionics Upgrade (CAU) is a proposed cockpit display upgrade designed to address human-factors usability issues of the current suite of cockpit displays, Multifunction Electronic Display System (MEDS). Unlike MEDS, CAU consolidates information in a task-oriented manner, rather than a data-source-oriented manner. CAU also makes greater use of color coding and graphical depictions in systems status presentations. An ascent-phase operation simulation study showed that CAU formats significantly improved the participants' abort-related situation awareness. Participants also performed certain malfunction management procedures more accurately when CAU was used. The Space Shuttles are now scheduled to be retired by 2010 without incorporating CAU; however, the results of the present study suggest that the human-centered design concepts are effective and can be extended to the cockpit interface design of NASA's next generation Crew Exploration Vehicle.

Towards Distributed Robot Control Systems

This paper describes ongoing research into the design of a distributed robot control system targeted for a robotic system consisting of several manipulators equipped with a dextrous robot hand, specifically the Salisbury hand. The goal of this research is to produce a high-level control network which will allow the robotic system to be used in a task-oriented manner, i.e. where actions of the hand are specified in terms of their effects on objects. In this paper, we discuss the research issues involve in the design of a logical distributed model of computation specifically for the robot domain, and in the design of a dynamic mapping function to realize this model using a network of processors. We also sketch our preliminary ideas towards addressing these issues.

Use of Contingent Social Reinforcement to Change the Verbal Expression of Motivation by Children of Differing Motivational Orientation

Ability to discriminate task-intrinsic from task-extrinsic sentences, and changes in choices of such sentences under differential verbal reinforcement, were investigated in 48 intrinsically motivated and 48 extrinsically motivated children. On each of 75 trials, two sentences were presented simultaneously to each. S. One of the sentences connoted task-intrinsic motivation and the other connoted task-extrinsic motivation. Ss' task was to choose one of the sentences in each pair and to read it aloud. One-third of the children in each group were socially reinforced (“good”) for choosing sentences indicative of intrinsic motivation; one-third were socially reinforced by choosing sentences indicative of extrinsic motivation; one-third were reinforced noncontingently. Children in the contingent reinforcement groups were able to discriminate the motivational statements, as reflected by significant effects of the contingent reinforcement on the frequency of their choices. Implications for a strategy for training persons to behave in a task-oriented manner are discussed.