Showing papers on "Adaptation (computer science) published in 2021"

A systematic global stocktake of evidence on human adaptation to climate change

Abstract: Assessing global progress on human adaptation to climate change is an urgent priority. Although the literature on adaptation to climate change is rapidly expanding, little is known about the actual extent of implementation. We systematically screened >48,000 articles using machine learning methods and a global network of 126 researchers. Our synthesis of the resulting 1,682 articles presents a systematic and comprehensive global stocktake of implemented human adaptation to climate change. Documented adaptations were largely fragmented, local and incremental, with limited evidence of transformational adaptation and negligible evidence of risk reduction outcomes. We identify eight priorities for global adaptation research: assess the effectiveness of adaptation responses, enhance the understanding of limits to adaptation, enable individuals and civil society to adapt, include missing places, scholars and scholarship, understand private sector responses, improve methods for synthesizing different forms of evidence, assess the adaptation at different temperature thresholds, and improve the inclusion of timescale and the dynamics of responses. Determining progress in adaptation to climate change is challenging, yet critical as climate change impacts increase. A stocktake of the scientific literature on implemented adaptation now shows that adaptation is mostly fragmented and incremental, with evidence lacking for its impact on reducing risk.

Domain Impression: A Source Data Free Domain Adaptation Method

Abstract: Unsupervised Domain adaptation methods solve the adaptation problem for an unlabeled target set, assuming that the source dataset is available with all labels. However, the availability of actual source samples is not always possible in practical cases. It could be due to memory constraints, privacy concerns, and challenges in sharing data. This practical scenario creates a bottleneck in the domain adaptation problem. This paper addresses this challenging scenario by proposing a domain adaptation technique that does not need any source data. Instead of the source data, we are only provided with a classifier that is trained on the source data. Our proposed approach is based on a generative framework, where the trained classifier is used for generating samples from the source classes. We learn the joint distribution of data by using the energy-based modeling of the trained classifier. At the same time, a new classifier is also adapted for the target domain. We perform various ablation analysis under different experimental setups and demonstrate that the proposed approach achieves better results than the baseline models in this extremely novel scenario.

The DUNE framework: Basic concepts and recent developments

Abstract: This paper presents the basic concepts and the module structure of the Distributed and Unified Numerics Environment and reflects on recent developments and general changes that happened since the release of the first Dune version in 2007 and the main papers describing that state Bastian etal. (2008a, 2008b). This discussion is accompanied with a description of various advanced features, such as coupling of domains and cut cells, grid modifications such as adaptation and moving domains, high order discretizations and node level performance, non-smooth multigrid methods, and multiscale methods. A brief discussion on current and future development directions of the framework concludes the paper.

Faster Domain Adaptation Networks

Abstract: It is widely acknowledged that the success of deep learning is built on large-scale training data and tremendous computing power. However, the data and computing power are not always available for many real-world applications. In this paper, we address the machine learning problem where it lacks training data and limits computing power. Specifically, we investigate domain adaptation which is able to transfer knowledge from one labeled source domain to an unlabeled target domain, so that we do not need much training data from the target domain. At the same time, we consider the situation that the running environment is confined, e.g., in edge computing the end device has very limited running resources. Technically, we present the Faster Domain Adaptation (FDA) protocol and further report two paradigms of FDA: early stopping and amid skipping. The former accelerates domain adaptation by multiple early exit points. The latter speeds up the adaptation by wisely skip several amid neural network blocks. Extensive experiments on standard benchmarks verify that our method is able to achieve the comparable and even better accuracy but employ much less computing resources. To the best of our knowledge, there are very few works which investigated accelerating knowledge adaptation in the community.

Autonomy in Physical Human-Robot Interaction: A Brief Survey

Abstract: Sharing the control of a robotic system with an autonomous controller allows a human to reduce his/her cognitive and physical workload during the execution of a task. In recent years, the development of inference and learning techniques has widened the spectrum of applications of shared control (SC) approaches, leading to robotic systems that are capable of seamless adaptation of their autonomy level. In this perspective, shared autonomy (SA) can be defined as the design paradigm that enables this adapting behavior of the robotic system. This letter collects the latest results achieved by the research community in the field of SC and SA with special emphasis on physical human-robot interaction (pHRI). Architectures and methods developed for SC and SA are discussed throughout the letter, highlighting the key aspects of each methodology. A discussion about open issues concludes this letter.

Interrogating ‘effectiveness’ in climate change adaptation: 11 guiding principles for adaptation research and practice

Abstract: The Paris Agreement articulates a global goal on adaptation, which aims to ensure an ‘adequate adaptation response’ to the ‘global temperature goal’, and requires countries to report progress through periodic global stocktakes. However, there remain conceptual and methodological challenges in defining an adaptation goal and mixed evidence on what effective adaptation looks like and how it can be enabled. In this review, we demonstrate how different normative views on adaptation outcomes, arising from different epistemological and disciplinary entry points, can lead to very different interpretations of adaptation effectiveness. We argue that how effectiveness is framed will significantly impact adaptation implementation and outcomes. This, furthermore, represents a way of exercising influence in adaptation decision-making. Eleven principles of effective adaptation are distilled as a way to pluralize guidance in international processes such as the Global Stocktake as well as national and sub-national exercises on tracking and monitoring adaptation.

Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview

Abstract: We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.

Adapting User Interfaces with Model-based Reinforcement Learning

Abstract: Adapting an interface requires taking into account both the positive and negative effects that changes may have on the user. A carelessly picked adaptation may impose high costs to the user – for example, due to surprise or relearning effort – or “trap” the process to a suboptimal design immaturely. However, effects on users are hard to predict as they depend on factors that are latent and evolve over the course of interaction. We propose a novel approach for adaptive user interfaces that yields a conservative adaptation policy: It finds beneficial changes when there are such and avoids changes when there are none. Our model-based reinforcement learning method plans sequences of adaptations and consults predictive HCI models to estimate their effects. We present empirical and simulation results from the case of adaptive menus, showing that the method outperforms both a non-adaptive and a frequency-based policy.

Task-adaptive Neural Process for User Cold-Start Recommendation

Abstract: User cold-start recommendation is a long-standing challenge for recommender systems due to the fact that only a few interactions of cold-start users can be exploited. Recent studies seek to address this challenge from the perspective of meta learning, and most of them follow a manner of parameter initialization, where the model parameters can be learned by a few steps of gradient updates. While these gradient-based meta-learning models achieve promising performances to some extent, a fundamental problem of them is how to adapt the global knowledge learned from previous tasks for the recommendations of cold-start users more effectively. In this paper, we develop a novel meta-learning recommender called task-adaptive neural process (TaNP). TaNP is a new member of the neural process family, where making recommendations for each user is associated with a corresponding stochastic process. TaNP directly maps the observed interactions of each user to a predictive distribution, sidestepping some training issues in gradient-based meta-learning models. More importantly, to balance the trade-off between model capacity and adaptation reliability, we introduce a novel task-adaptive mechanism. It enables our model to learn the relevance of different tasks and customize the global knowledge to the task-related decoder parameters for estimating user preferences. We validate TaNP on multiple benchmark datasets in different experimental settings. Empirical results demonstrate that TaNP yields consistent improvements over several state-of-the-art meta-learning recommenders.

Adversarial Multiple-Target Domain Adaptation for Fault Classification

Abstract: Data-driven fault classification methods are receiving great attention as they can be applied to many real-world applications. However, they work under the assumption that training data and testing data are drawn from the same distribution. Practical scenarios have varying operating conditions, which results in a domain-shift problem that significantly deteriorates the diagnosis performance. Recently, domain adaptation (DA) has been explored to address the domain-shift problem by transferring the knowledge from labeled source domain (e.g., source working condition) to unlabeled target domain (e.g., target working condition). Yet, all the existing methods are working under single-source single-target (1S1T) settings. Hence, a new model needs to be trained for each new target domain. This shows limited scalability in handling multiple working conditions since different models should be trained for different target working conditions, which is clearly not a viable solution in practice. To address this problem, we propose a novel adversarial multiple-target DA (AMDA) method for single-source multiple-target (1SmT) scenario, where the model can generalize to multiple-target domains concurrently. Adversarial adaptation is applied to transform the multiple-target domain features to be invariant from the single-source-domain features. This leads to a scalable model with a novel capability of generalizing to multiple-target domains. Extensive experiments on two public datasets and one self-collected dataset have demonstrated that the proposed method outperforms state-of-the-art methods consistently. Our source codes and data are available at https://github.com/mohamedr002/AMDA .

Cultural adaptation challenges and strategies during study abroad: New Zealand students in China

Abstract: The rising popularity of the Chinese language as a subject for study has motivated research on international students’ cultural adaptation and language learning during periods of study abroad in Ch...

Applying Machine Learning in Self-Adaptive Systems: A Systematic Literature Review

Abstract: Recently, we witness a rapid increase in the use of machine learning in self-adaptive systems. Machine learning has been used for a variety of reasons, ranging from learning a model of the environment of a system during operation to filtering large sets of possible configurations before analysing them. While a body of work on the use of machine learning in self-adaptive systems exists, there is currently no systematic overview of this area. Such overview is important for researchers to understand the state of the art and direct future research efforts. This paper reports the results of a systematic literature review that aims at providing such an overview. We focus on self-adaptive systems that are based on a traditional Monitor-Analyze-Plan-Execute feedback loop (MAPE). The research questions are centred on the problems that motivate the use of machine learning in self-adaptive systems, the key engineering aspects of learning in self-adaptation, and open challenges. The search resulted in 6709 papers, of which 109 were retained for data collection. Analysis of the collected data shows that machine learning is mostly used for updating adaptation rules and policies to improve system qualities, and managing resources to better balance qualities and resources. These problems are primarily solved using supervised and interactive learning with classification, regression and reinforcement learning as the dominant methods. Surprisingly, unsupervised learning that naturally fits automation is only applied in a small number of studies. Key open challenges in this area include the performance of learning, managing the effects of learning, and dealing with more complex types of goals. From the insights derived from this systematic literature review we outline an initial design process for applying machine learning in self-adaptive systems that are based on MAPE feedback loops.

Adapting Software with Affective Computing: A Systematic Review

Abstract: Strategies aimed at keeping the user's interest in using computer applications are being studied to provide greater user engagement, and can influence how people interact with computers. One of the approaches that can promote user engagement is Affective Computing (AC), based on the premise of recognizing the user's emotional state and adjusting the computer application to respond to such state in real-time. Although it is a relatively new area, over the past few years many research works have investigated the use of AC in various activities and objectives. To provide an overview on the use of AC in computer applications, this article presents a systematic literature review based on available articles on the main scientific databases of the Computer Science area. The main contribution of this review is the analysis of different types of applications. Based on the 58 articles analyzed, the main emotion recognition techniques and approaches to the adaptation of computer applications, as well as the limitations and challenges to be overcome were compiled. Our conclusions present the limitations and challenges still to be overcome in the area of automatic adaptation of computer applications by means of AC.

Did We Get Sensorimotor Adaptation Wrong? Implicit Adaptation as Direct Policy Updating Rather than Forward-Model-Based Learning.

Abstract: The human motor system can rapidly adapt its motor output in response to errors. The prevailing theory of this process posits that the motor system adapts an internal forward model that predicts the consequences of outgoing motor commands and uses this forward model to plan future movements. However, despite clear evidence that adaptive forward models exist and are used to help track the state of the body, there is no definitive evidence that such models are used in movement planning. An alternative to the forward-model-based theory of adaptation is that movements are generated based on a learned policy that is adjusted over time by movement errors directly (“direct policy learning”). This learning mechanism could act in parallel with, but independent of, any updates to a predictive forward model. Forward-model-based learning and direct policy learning generate very similar predictions about behavior in conventional adaptation paradigms. However, across three experiments with human participants (N = 47, 26 female), we show that these mechanisms can be dissociated based on the properties of implicit adaptation under mirror-reversed visual feedback. Although mirror reversal is an extreme perturbation, it still elicits implicit adaptation; however, this adaptation acts to amplify rather than to reduce errors. We show that the pattern of this adaptation over time and across targets is consistent with direct policy learning but not forward-model-based learning. Our findings suggest that the forward-model-based theory of adaptation needs to be re-examined and that direct policy learning provides a more plausible explanation of implicit adaptation. SIGNIFICANCE STATEMENT The ability of our brain to adapt movements in response to error is one of the most widely studied phenomena in motor learning. Yet, we still do not know the process by which errors eventually result in adaptation. It is known that the brain maintains and updates an internal forward model, which predicts the consequences of motor commands, and the prevailing theory of motor adaptation posits that this updated forward model is responsible for trial-by-trial adaptive changes. Here, we question this view and show instead that adaptation is better explained by a simpler process whereby motor output is directly adjusted by task errors. Our findings cast doubt on long-held beliefs about adaptation.

Smart building management system: Performance specifications and design requirements

Abstract: In a smart building, physical and computational elements are integrated to create an environment that is energy-efficient, comfortable, and safe for its occupants The design and development of smart buildings is a complicated task Every smart building is a unique structure from the requirements and characteristics standpoints Therefore, achieving reliability and real-time adaptation to environmental conditions are some of the challenges involved in smart building development Resolving these issues requires deep insights into control theory, machine learning, system specifications, and design requirements To address this need, this paper proposes a real-time management system for controlling various aspects of smart buildings (indoor conditions, comfort criteria, security, safety, and costs), and also presents the performance specifications, design requirements, and operating constraints for these systems The study aims to address two less-attended problems in the related literature of building management and control First, only a few studies have attempted to include real-time learning of buildings' subjective parameters in the model-based control design Second, to the best of the authors' knowledge, smart building management studies are primarily focused on optimizing thermal or visual aspects of buildings, and little attention is given to the simultaneous management of all building subsystems and objectives; ie, considering buildings' physical models, environmental conditions, comfort specifications, and occupants’ preferences and safety in the design Accordingly, in this paper, we combine machine learning with model-based control approaches to incorporate subjective environmental parameters into the building management structure In addition, another benefit of this study is that it integrates model-based and learning-based control schemes in a unified management structure for controlling various aspects of building performance The proposed building management system can be applied to a variety of smart buildings in which the building parameters can be monitored and self-tuned using a well-defined set of control inputs

SemanticAdapt: Optimization-based Adaptation of Mixed Reality Layouts Leveraging Virtual-Physical Semantic Connections

Abstract: We present an optimization-based approach that automatically adapts Mixed Reality (MR) interfaces to different physical environments. Current MR layouts, including the position and scale of virtual interface elements, need to be manually adapted by users whenever they move between environments, and whenever they switch tasks. This process is tedious and time consuming, and arguably needs to be automated for MR systems to be beneficial for end users. We contribute an approach that formulates this challenge as a combinatorial optimization problem and automatically decides the placement of virtual interface elements in new environments. To achieve this, we exploit the semantic association between the virtual interface elements and physical objects in an environment. Our optimization furthermore considers the utility of elements for users’ current task, layout factors, and spatio-temporal consistency to previous layouts. All those factors are combined in a single linear program, which is used to adapt the layout of MR interfaces in real time. We demonstrate a set of application scenarios, showcasing the versatility and applicability of our approach. Finally, we show that compared to a naive adaptive baseline approach that does not take semantic associations into account, our approach decreased the number of manual interface adaptations by 33%.

Adapting User Interfaces with Model-based Reinforcement Learning

Abstract: Adapting an interface requires taking into account both the positive and negative effects that changes may have on the user. A carelessly picked adaptation may impose high costs to the user -- for example, due to surprise or relearning effort -- or "trap" the process to a suboptimal design immaturely. However, effects on users are hard to predict as they depend on factors that are latent and evolve over the course of interaction. We propose a novel approach for adaptive user interfaces that yields a conservative adaptation policy: It finds beneficial changes when there are such and avoids changes when there are none. Our model-based reinforcement learning method plans sequences of adaptations and consults predictive HCI models to estimate their effects. We present empirical and simulation results from the case of adaptive menus, showing that the method outperforms both a non-adaptive and a frequency-based policy.

A digital servitization framework for viable manufacturing companies

Abstract: The purpose of this paper is to understand the strategic management of a technology-enabled shift from a product-centric to a service-centric logic and to identify the sociotechnical dynamics underlying this transition. The study focuses on how manufacturers manage to create value in industrial markets through digital servitization.,An abductive research approach is used to investigate two manufacturing firms, and an interpretive framework is used as an analytical template. A cross-case analysis is conducted.,The case companies strategically managed sociotechnical processes of digitization to co-create value. Their service orientation delineates dissimilarity in terms of digital servitization. It reflects a viable ecosystem that moves toward datatization through adaptation in one case and a viable ecosystem that moves toward digitization through reconfiguration in the other case.,A theoretically grounded, empirically informed framework is proposed to detect transformational mechanisms to manage value co-creation in digitally servitized contexts, thus contributing to ecosystem viability.,This is the first study to adopt a system perspective such as the viable system approach combined with service-dominant logic to reconceptualize the overall sociotechnical processes and the underlying mechanisms leading to digitized value creation. In line with a systems view and a systematic process based on a transformative attitude toward digital servitization, the empirically informed framework identifies specific co-creation activities and recursive feedback loops.

Attention-Based Deep Learning Framework for Human Activity Recognition With User Adaptation

Abstract: Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled by modern ubiquitous computing devices. While several techniques based on hand-crafted feature engineering have been proposed, the current state-of-the-art is represented by deep learning architectures that automatically obtain high level representations and that use recurrent neural networks (RNNs) to extract temporal dependencies in the input. RNNs have several limitations, in particular in dealing with long-term dependencies. We propose a novel deep learning framework, TrASenD, based on a purely attention-based mechanism, that overcomes the limitations of the state-of-the-art. We show that our proposed attention-based architecture is considerably more powerful than previous approaches, with an average increment, of more than 7% on the F1 score over the previous best performing model. Furthermore, we consider the problem of personalizing HAR deep learning models, which is of great importance in several applications. We propose a simple and effective transfer-learning based strategy to adapt a model to a specific user, providing an average increment of 6% on the F1 score on the predictions for that user. Our extensive experimental evaluation proves the significantly superior capabilities of our proposed framework over the current state-of-the-art and the effectiveness of our user adaptation technique.

‘The best guess for the future?’ : Teachers’ adaptation to open and flexible learning environments in Finland

Abstract: Finnish education has recently experienced reforms with respect to guidelines forming the curriculum framework for basic education and school architecture. Since 2016, all new schools incorporate o...

A Synthesis of the Many Errors and Learning Processes of Visuomotor Adaptation

Abstract: Visuomotor adaptation has one of the oldest experimental histories in psychology and neuroscience, yet its precise nature has always been a topic of debate. Here we offer a survey and synthesis of recent work on visuomotor adaptation that we hope will prove illuminating for this ongoing dialogue. We discuss three types of error signals that drive learning in adaptation tasks: task performance error, sensory prediction-error, and a binary target hitting error. Each of these errors has been shown to drive distinct learning processes. Namely, both target hitting errors and putative sensory prediction-errors drive an implicit change in visuomotor maps, while task performance error drives learning of explicit strategy use and non-motor decision-making. Each of these learning processes contributes to the overall learning that takes place in visuomotor adaptation tasks, and although the learning processes and error signals are independent, they interact in a complex manner. We outline many task contexts where the operation of these processes is counter-intuitive and offer general guidelines for their control, measurement and interpretation. We believe this new framework unifies several disparate threads of research in sensorimotor adaptation that often seem in conflict. We conclude by explaining how this more nuanced understanding of errors and learning processes could lend itself to the analysis of other types of sensorimotor adaptation, of motor skill learning, of the neural processing underlying sensorimotor adaptation in humans, of animal models and of brain computer interfaces.