Search Results (10)

Material-resolving computed tomography is a powerful and well-proven tool for various clinical applications. For industrial scan setups and materials, several problems, such as K-edge absence and beam hardening, prevent the direct transfer of these methods. This work applies dual-energy computed tomography methods for material decomposition to simulated phantoms composed of industry-relevant materials such as magnesium, aluminium and iron, as well as some commonly used alloys like Al–Si and Ti64. Challenges and limitations for multi-material decomposition are discussed in the context of X-ray absorption physics, which provides spectral information that can be ambiguous. A deep learning model, derived from a clinical use case and based on the popular U-Net, was utilised in this study. For various reasons outlined below, the training dataset was simulated, whereby phantom shapes and material properties were sampled arbitrarily. The detector signal is computed by a forward projector followed by Beer–Lambert law integration. Our trained model could predict two-material systems with different elements, achieving a relative error of approximately 1% through simulated data. For the discrimination of the element titanium and its alloy Ti64, which were also simulated, the relative error increased to 5% due to their similar X-ray absorption coefficients. To access authentic CT data, the model underwent testing using a 10c euro coin composed of an alloy known as Nordic gold. The model detected copper as the main constituent correctly, but the relative fraction, which should be 89%, was predicted to be ≈70%. Full article

Manufacturing industries require the efficient and voluminous production of high-quality finished goods. In the context of Industry 4.0, visual anomaly detection poses an optimistic solution for automatically controlled product quality with high precision. In general, automation based on computer vision is a promising solution to prevent bottlenecks at the product quality checkpoint. We considered recent advancements in machine learning to improve visual defect localization, but challenges persist in obtaining a balanced feature set and database of the wide variety of defects occurring in the production line. Hence, this paper proposes a defect localizing autoencoder with unsupervised class selection by clustering with k-means the features extracted from a pretrained VGG16 network. Moreover, the selected classes of defects are augmented with natural wild textures to simulate artificial defects. The study demonstrates the effectiveness of the defect localizing autoencoder with unsupervised class selection for improving defect detection in manufacturing industries. The proposed methodology shows promising results with precise and accurate localization of quality defects on melamine-faced boards for the furniture industry. Incorporating artificial defects into the training data shows significant potential for practical implementation in real-world quality control scenarios. Full article

Machine learning (ML) has become increasingly prevalent in various domains. However, ML algorithms sometimes give unfair outcomes and discrimination against certain groups. Thereby, bias occurs when our results produce a decision that is systematically incorrect. At various phases of the ML pipeline, such as data collection, pre-processing, model selection, and evaluation, these biases appear. Bias reduction methods for ML have been suggested using a variety of techniques. By changing the data or the model itself, adding more fairness constraints, or both, these methods try to lessen bias. The best technique relies on the particular context and application because each technique has advantages and disadvantages. Therefore, in this paper, we present a comprehensive survey of bias mitigation techniques in machine learning (ML) with a focus on in-depth exploration of methods, including adversarial training. We examine the diverse types of bias that can afflict ML systems, elucidate current research trends, and address future challenges. Our discussion encompasses a detailed analysis of pre-processing, in-processing, and post-processing methods, including their respective pros and cons. Moreover, we go beyond qualitative assessments by quantifying the strategies for bias reduction and providing empirical evidence and performance metrics. This paper serves as an invaluable resource for researchers, practitioners, and policymakers seeking to navigate the intricate landscape of bias in ML, offering both a profound understanding of the issue and actionable insights for responsible and effective bias mitigation. Full article

Animal-assisted pedagogy is well known in classroom practice, but scientific evidence of its impact on teaching and learning conditions is still lacking. At the same time, the biggest challenge in education systems worldwide is the social inclusion of students. In a pre–post design, 30 heterogeneous students (16 f/14 m) from four different school classes (grades 5–8) of two secondary schools and one grammar school were interviewed (in a problem-centered interview) about their social inclusion and their social climate in class before and after being taught selected subjects with a school dog for one school term. At the second measurement point, participants were also asked about their perception of animal-assisted pedagogy. The qualitative data analysis (Kuckartz) showed that the presence of a dog leads to an improved social climate, more social integration and to a change in social roles; therefore, we discussed our findings in the context of role theory (Krappmann). In addition, we found that the mutual perception of the other students and the teacher changes to a more positive and friendlier image. Through animal-assisted pedagogy, a new social role is added to the classroom, where caring and bonding are prioritized. Social interaction and norms are influenced and stereotypical and individual roles can be changed. Therefore, animal-assisted pedagogy can be key to promoting social inclusion in the school environment. Full article

The COVID-19 pandemic forced the authorities to take an unprecedented measure in history: the house confinement of millions of people worldwide. Video games, especially open-world video games (OWVGs), became meeting spaces, a digital places to play, chat, learn and socialize due to the context of the health crisis, respecting the rules of social distancing. This article analyses the role of video games and, more specifically, OWVGs, as playgrounds and training spaces during the pandemic. Statistical data and analyses carried out by consulting companies and civil associations show the definitive insertion of these video games in our routine and social relations. The challenge is to take advantage of the skills and abilities that these video games develop within a new framework of individual and community learning. The conclusions of the research show that the virtual worlds of video games are for the new digital society, safe and comfortable meeting spaces, and that since the confinement, these digital places have greatly expanded their reach, previously only limited to the gamer community. Full article

In recent years, the use of deep learning in language models has gained much attention. Some research projects claim that they can generate text that can be interpreted as human writing, enabling new possibilities in many application areas. Among the different areas related to language processing, one of the most notable in applying this type of modeling is programming languages. For years, the machine learning community has been researching this software engineering area, pursuing goals like applying different approaches to auto-complete, generate, fix, or evaluate code programmed by humans. Considering the increasing popularity of the deep learning-enabled language models approach, we found a lack of empirical papers that compare different deep learning architectures to create and use language models based on programming code. This paper compares different neural network architectures like Average Stochastic Gradient Descent (ASGD) Weight-Dropped LSTMs (AWD-LSTMs), AWD-Quasi-Recurrent Neural Networks (QRNNs), and Transformer while using transfer learning and different forms of tokenization to see how they behave in building language models using a Python dataset for code generation and filling mask tasks. Considering the results, we discuss each approach’s different strengths and weaknesses and what gaps we found to evaluate the language models or to apply them in a real programming context. Full article

Wearable mobile eye trackers have great potential as they allow the measurement of eye movements during daily activities such as driving, navigating the world and doing groceries. Although mobile eye trackers have been around for some time, developing and operating these eye trackers was generally a highly technical affair. As such, mobile eye-tracking research was not feasible for most labs. Nowadays, many mobile eye trackers are available from eye-tracking manufacturers (e.g., Tobii, Pupil labs, SMI, Ergoneers) and various implementations in virtual/augmented reality have recently been released.The wide availability has caused the number of publications using a mobile eye tracker to increase quickly. Mobile eye tracking is now applied in vision science, educational science, developmental psychology, marketing research (using virtual and real supermarkets), clinical psychology, usability, architecture, medicine, and more. Yet, transitioning from lab-based studies where eye trackers are fixed to the world to studies where eye trackers are fixed to the head presents researchers with a number of problems. These problems range from the conceptual frameworks used in world-fixed and head-fixed eye tracking and how they relate to each other, to the lack of data quality comparisons and field tests of the different mobile eye trackers and how the gaze signal can be classified or mapped to the visual stimulus. Such problems need to be addressed in order to understand how world-fixed and head-fixed eye-tracking research can be compared and to understand the full potential and limits of what mobile eye-tracking can deliver. In this symposium, we bring together presenting researchers from five different institutions (Lund University, Utrecht University, Clemson University, Birkbeck University of London and Rochester Institute of Technology) addressing problems and innovative solutions across the entire breadth of mobile eye-tracking research. Hooge, presenting Hessels et al. paper, focus on the definitions of fixations and saccades held by researchers in the eyemovement field and argue how they need to be clarified in order to allow comparisons between world-fixed and head-fixed eye-tracking research.—Diaz et al. introduce machine-learning techniques for classifying the gaze signal in mobile eye-tracking contexts where head and body are unrestrained. Niehorster et al. compare data quality of mobile eye trackers during natural behavior and discuss the application range of these eye trackers. Duchowski et al. introduce a method for automatically mapping gaze to faces using computer vision techniques. Pelz et al. employ state-of-the-art techniques to map fixations to objects of interest in the scene video and align grasp and eye-movement data in the same reference frame to investigate the guidance of eye movements during manual interaction. Full article

This paper explores map users' cognitive processes in learning, acquiring and remembering information presented via screen maps. In this context, we conducted a mixed-methods user experiment employing digital sketch maps and eye tracking. On the one hand, the performance of the participants was assessed based on the order with which the objects were drawn and the influence of visual variables (e.g., presence & location, size, shape, color). On the other hand, trial durations and eye tracking statistics such as average duration of fixations, and number of fixations per seconds were compared. Moreover, selected AoIs (Area of Interests) were explored to gain a deeper insight on visual behavior of map users. Depending on the normality of the data, we used either two-way ANOVA or Mann-Whitney U test to inspect the significance of the results. Based on the evaluation of the drawing order, we observed that experts and males drew roads first whereas; novices and females focused more on hydrographic object. According to the assessment of drawn elements, no significant differences emerged between neither experts and novices, nor females and males for the retrieval of spatial information presented on 2D maps with a simple design and content. The differences in trial durations between novices and experts were not statistically significant while both studying and drawing. Similarly, no significant difference occurred between female and male participants for either studying or drawing. Eye tracking metrics also supported these findings. For average duration of fixation, there was found no significant difference between experts and novices, as well as between females and males. Similarly, no significant differences were found for the mean number of fixation. Full article

The grand goal of Machine Learning is to develop software which can learn from previous experience—similar to how we humans do. Ultimately, to reach a level of usable intelligence, we need (1) to learn from prior data, (2) to extract knowledge, (3) to generalize—i.e., guessing where probability function mass/density concentrates, (4) to fight the curse of dimensionality, and (5) to disentangle underlying explanatory factors of the data—i.e., to make sense of the data in the context of an application domain. To address these challenges and to ensure successful machine learning applications in various domains an integrated machine learning approach is important. This requires a concerted international effort without boundaries, supporting collaborative, cross-domain, interdisciplinary and transdisciplinary work of experts from seven sections, ranging from data pre-processing to data visualization, i.e., to map results found in arbitrarily high dimensional spaces into the lower dimensions to make it accessible, usable and useful to the end user. An integrated machine learning approach needs also to consider issues of privacy, data protection, safety, security, user acceptance and social implications. This paper is the inaugural introduction to the new journal of MAchine Learning & Knowledge Extraction (MAKE). The goal is to provide an incomplete, personally biased, but consistent introduction into the concepts of MAKE and a brief overview of some selected topics to stimulate future research in the international research community. Full article

The C57BL/6 (B6) mouse is the background strain most frequently used for genetically-modified mice. Previous studies have found significant behavioral and genetic differences between the B6J (The Jackson Laboratory) and B6N substrains (National Institutes of Health); however, most studies employed only male mice. We performed a comprehensive battery of motor function and learning and memory tests on male and female mice from both substrains. The B6N male mice had greater improvement in the rotarod test. In contrast, B6J female mice had longer latencies to falling from the rotarod. In the Morris water maze (MWM), B6J males had significantly shorter latencies to finding the hidden platform. However, B6N females had significantly shorter path lengths in the reversal and shifted-reduced phases. In open field locomotor activity, B6J males had higher activity levels, whereas B6N females took longer to habituate. In the fear conditioning test, B6N males had a significantly longer time freezing in the new context compared with B6J males, but no significant differences were found in contextual or cued tests. In summary, our findings demonstrate the importance of testing both males and females in neurobehavioral studies. Both factors (sex and substrain) must be taken into account when designing developmental neurotoxicology studies. Full article