Explore the vast range of titles available.

The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which gives rise to uncertainties due to subjectivity. Since the microstructure could be a combination of different phases or constituents with complex substructures its automatic classification is very challenging and only a few prior studies exist. Prior works focused on designed and engineered features by experts and classified microstructures separately from the feature extraction step. Recently, Deep Learning methods have shown strong performance in vision applications by learning the features from data together with the classification step. In this work, we propose a Deep Learning method for microstructural classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Network (FCNN) accompanied by a max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy. Beyond the strong performance of our method, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation.

[The authors] propose the self-regulation view in writing-to-learn as a promising theoretical perspective that draws on models of self-regulated learning theory and cognitive load theory. According to this theoretical perspective, writing has the potential to scaffold self-regulated learning due to the cognitive offloading written text generally offers as an external representation and memory aid, and due to the offloading, that specifically results from the genre-free principle in journal writing. However, to enable learners to optimally exploit this learning opportunity, the journal writing needs to be instructionally supported. Accordingly, [the authors] have set up a research program - the Freiburg Self-Regulated-Journal-Writing Approach - in which [the authors] developed and tested different instructional support methods to foster learning outcomes by optimizing cognitive load during self-regulated learning by journal writing. [The authors] will highlight the main insights of [their] research program which are synthesized from 16 experimental and 4 correlative studies published in 16 original papers. Accordingly, [the authors] present results on (1) the effects of prompting germane processing in journal writing, (2) the effects of providing worked examples and metacognitive information to support students in effectively exploiting prompted journal writing for self-regulated learning, (3) the effects of adapting and fading guidance in line with learners' expertise in self-regulated learning, and (4) the effects of journal writing on learning motivation and motivation to write. The article closes with a discussion of several avenues of how the Freiburg Self-Regulated-Journal-Writing Approach can be developed further to advance research that integrates self-regulated learning with cognitive load theory. (Orig.).

Personalized education-the systematic adaptation of instruction to individual learners-has been a long-striven goal. We review research on personalized education that has been conducted in the laboratory, in the classroom, and in digital learning environments. Across all learning environments, we find that personalization is most successful when relevant learner characteristics are measured repeatedly during the learning process and when these data are used to adapt instruction in a systematic way. Building on these observations, we propose a novel, dynamic framework of personalization that conceptualizes learners as dynamic entities that change during and in interaction with the instructional process. As these dynamics manifest on different timescales, so do the opportunities for instructional adaptations-ranging from setting appropriate learning goals at the macroscale to reacting to affective-motivational fluctuations at the microscale. We argue that instructional design needs to take these dynamics into account in order to adapt to a specific learner at a specific point in time. Finally, we provide some examples of successful, dynamic adaptations and discuss future directions that arise from a dynamic conceptualization of personalization. (DIPF/Orig.)

As robots are entering into educational fields to enhance children’s learning, it becomes relevant to explore different methods of learning in the area of child–robot interaction. In this article, we present an autonomous educational system incorporating a social robot to enhance children’s handwriting skills. The system provides a one-to-one learning scenario based on the learning-by-teaching approach where a tutor-child assess the handwriting skills of a learner-robot. The robot’s writing was generated by an algorithm incorporating human-inspired movements and could reproduce a set of writing errors. We tested the system by conducting two multi-session studies. In the first study, we assigned the robot two contrasting competencies: ‘learning’ and ‘non-learning’. We measured the differences in children’s learning gains and changes in their perceptions of the learner-robot. The second study followed a similar interaction scenario and research questions, but this time the robot performed three learning competencies: ‘continuous-learning’; ‘non-learning’ and ‘personalised-learning’. The findings of these studies show that the children learnt with the robot that exhibits learning competency and children’s learning and perceptions of the robot changed as interactions unfold, confirming the need for longitudinal studies. This research supports that the contrasting learning competencies of social robots can impact children’s learning differently in peer-learning scenarios.

We propose an approach to efficiently teach robots how to perform dynamic manipulation tasks in cooperation with a human partner. The approach utilises human sensorimotor learning ability where the human tutor controls the robot through a multi-modal interface to make it perform the desired task. During the tutoring, the robot simultaneously learns the action policy of the tutor and through time gains full autonomy. We demonstrate our approach by an experiment where we taught a robot how to perform a wood sawing task with a human partner using a two-person cross-cut saw. The challenge of this experiment is that it requires precise coordination of the robot’s motion and compliance according to the partner’s actions. To transfer the sawing skill from the tutor to the robot we used Locally Weighted Regression for trajectory generalisation, and adaptive oscillators for adaptation of the robot to the partner’s motion.

Brain disorders comprise several psychiatric and neurological disorders which can be characterized by impaired cognition, mood alteration, psychosis, depressive episodes, and neurodegeneration. Clinical diagnoses primarily rely on a combination of life history information and questionnaires, with a distinct lack of discriminative biomarkers in use for psychiatric disorders. Symptoms across brain conditions are associated with functional alterations of cognitive and emotional processes, which can correlate with anatomical variation; structural magnetic resonance imaging (MRI) data of the brain are therefore an important focus of research, particularly for predictive modelling. With the advent of large MRI data consortia (such as the Alzheimer's Disease Neuroimaging Initiative) facilitating a greater number of MRI‐based classification studies, convolutional neural networks (CNNs)—deep learning models well suited to image processing tasks—have become increasingly popular for research into brain conditions. This has resulted in a myriad of studies reporting impressive predictive performances, demonstrating the potential clinical value of deep learning systems. However, methodologies can vary widely across studies, making them difficult to compare and/or reproduce, potentially limiting their clinical application. Here, we conduct a qualitative systematic literature review of 55 studies carrying out CNN‐based predictive modelling of brain disorders using MRI data and evaluate them based on three principles—modelling practices, transparency, and interpretability. We propose several recommendations to enhance the potential for the integration of CNNs into clinical care. Predictive modelling of brain disorders using convolutional neural networks applied to structural neuroimaging data has become popular in recent years. We systematically review 55 papers in the field and evaluate their modelling practices, transparency, and considerations of interpretability.

This research considers a specific incremental sheet metal free-forming process, which allows for individualized component manufacturing. However, for a reasonable application in practice, an automation of the manual process is mandatory. Unfortunately, up to now, no general tool path generation strategies are available when free-forming processes are to be utilized. On this account, for the investigated driving process, a holistic concept for deriving tool paths for the production of sheet metal parts directly from a digital component model is presented adopting an artificial neural network architecture. Consequently, for the very first time an automated part production is possible in incremental sheet metal free-forming applications. For this, a suitable network input and output structure is designed. Balanced sample data sets are generated for appropriate training. An associated network topology is determined and undergoes a training and testing phase. The influence of different training algorithms, network configurations, as well as training sets have been studied in relation to a feedforward network structure with backpropagation. Finally, the proposed computer integrated manufacturing system is subject to validation and verification by automated sheet part production, which is followed by concluding remarks on the capabilities and limits of the concept.

Background Nuclear pleomorphism and tumor microenvironment (TME) play a critical role in cancer development and progression. Identifying most predictive nuclei and TME features of basal cell carcinoma (BCC) may provide insights into which characteristics pathologists can use to distinguish and stratify this entity. Objectives To develop an automated workflow based on nuclei and TME features from basaloid cell tumor regions to differentiate BCC from trichoepithelioma (TE) and stratify BCC into high‐risk (HR) and low‐risk (LR) subtypes, and to identify the nuclear and TME characteristics profile of different basaloid cell tumors. Methods The deep learning systems were trained on 161 H&E ‐stained sections which contained 51 sections of HR‐BCC, 50 sections of LR‐BCC and 60 sections of TE from one institution (D1), and externally and independently validated on D2 (46 sections) and D3 (76 sections), from 2015 to 2022. 60%, 20% and 20% of D1 data were randomly splitted for training, validation and testing, respectively. The framework comprised four stages: tumor regions identification by multi‐head self‐attention (MSA) U‐Net, nuclei segmentation by HoVer‐Net, quantitative feature by handcrafted extraction, and differentiation and risk stratification classifier construction. Pixel accuracy, precision, recall, dice score, intersection over union (IoU) and area under the curve (AUC) were used to evaluate the performance of tumor segmentation model and classifiers. Results MSA‐U‐Net model detected tumor regions with 0.910 precision, 0.869 recall, 0.889 dice score and 0.800 IoU. The differentiation classifier achieved 0.977 ± 0.0159, 0.955 ± 0.0181, 0.885 ± 0.0237 AUC in D1, D2 and D3, respectively. The most discriminative features between BCC and TE contained Homogeneity, Elongation, T‐T_meanEdgeLength, T‐T_Nsubgraph, S‐T_HarmonicCentrality, S‐S_Degrees. The risk stratification model can well predict HR‐BCC and LR‐BCC with 0.920 ± 0.0579, 0.839 ± 0.0176, 0.825 ± 0.0153 AUC in D1, D2 and D3, respectively. The most discriminative features between HR‐BCC and LR‐BCC comprised IntensityMin, Solidity, T‐T_minEdgeLength, T‐T_Coreness, T‐T_Degrees, T‐T_Betweenness, S‐T_Degrees. Conclusions This framework hold potential for future use as a second opinion helping inform diagnosis of BCC, and identify nuclei and TME features related with malignancy and tumor risk stratification.

Cognitive radios are expected to play a major role towards meeting the exploding traffic demand over wireless systems. A cognitive radio node senses the environment, analyzes the outdoor parameters, and then makes decisions for dynamic time-frequency-space resource allocation and management to improve the utilization of the radio spectrum. For efficient real-time process, the cognitive radio is usually combined with artificial intelligence and machine-learning techniques so that an adaptive and intelligent allocation is achieved. This paper firstly presents the cognitive radio networks, resources, objectives, constraints, and challenges. Then, it introduces artificial intelligence and machine-learning techniques and emphasizes the role of learning in cognitive radios. Then, a survey on the state-of-the-art of machine-learning techniques in cognitive radios is presented. The literature survey is organized based on different artificial intelligence techniques such as fuzzy logic, genetic algorithms, neural networks, game theory, reinforcement learning, support vector machine, case-based reasoning, entropy, Bayesian, Markov model, multi-agent systems, and artificial bee colony algorithm. This paper also discusses the cognitive radio implementation and the learning challenges foreseen in cognitive radio applications.

In a wireless sensor network (WSN), there is always the possibility of failure in sensor nodes. Quality of Service (QoS) of WSNs is highly degraded due to the faulty sensor nodes. One solution to this problem is to detect and reuse faulty sensor nodes as much as possible. Accordingly, QoS of WSNs can be improved. This paper proposes a distributed cellular learning automata faulty node classification and management scheme for WSNs that can detect and reuse faulty sensor nodes according to their fault status. The proposed method uses cellular learning automata to assign a status to each node based on hardware conditions, which makes the nodes do one of the network’s operations. The proposed algorithm is experimented extensively and the results are compared with the existing algorithms to demonstrate the effectiveness of the proposed algorithm.