Human Learning Process Research Articles

Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systems

Anomaly detection is critical to ensure the security of cyber-physical systems (CPS) . However, due to the increasing complexity of attacks and CPS themselves, anomaly detection in CPS is becoming more and more challenging. In our previous work, we proposed a digital twin-based anomaly detection method, called ATTAIN, which takes advantage of both historical and real-time data of CPS. However, such data vary significantly in terms of difficulty. Therefore, similar to human learning processes, deep learning models (e.g., ATTAIN) can benefit from an easy-to-difficult curriculum. To this end, in this paper, we present a novel approach, named digitaL twin-based Anomaly deTecTion wIth Curriculum lEarning ( LATTICE ) , which extends ATTAIN by introducing curriculum learning to optimize its learning paradigm. LATTICE attributes each sample with a difficulty score, before being fed into a training scheduler. The training scheduler samples batches of training data based on these difficulty scores such that learning from easy to difficult data can be performed. To evaluate LATTICE, we use five publicly available datasets collected from five real-world CPS testbeds. We compare LATTICE with ATTAIN and two other state-of-the-art anomaly detectors. Evaluation results show that LATTICE outperforms the three baselines and ATTAIN by 0.906%-2.367% in terms of the F1 score. LATTICE also, on average, reduces the training time of ATTAIN by 4.2% on the five datasets and is on par with the baselines in terms of detection delay time.

Boost your brain: a simple 100% normobaric oxygen treatment improves human motor learning processes.

Human motor learning processes are a fundamental part of our daily lives and can be adversely affected by neurologic conditions. Motor learning largely depends on successfully integrating cognitive and motor-related sensory information, and a simple, easily accessible treatment that could enhance such processes would be exciting and clinically impactful. Normobaric 100% oxygen treatment (NbOxTr) is often used as a first-line intervention to improve survival rates of brain cells in neurological trauma, and recent work indicates that improvements in elements crucial for cognitive-motor-related functions can occur during NbOxTr. However, whether NbOxTr can enhance the motor learning processes of healthy human brains is unknown. Here, we investigated whether a brief NbOxTr administered via nasal cannula improves motor learning processes during a visuomotor adaptation task where participants adapt to a visual distortion between visual feedback and hand movements. 40 healthy young adults (M = 21 years) were randomly assigned to a NbOxTr (N = 20; 100% oxygen) or air (N = 20; regular air) group and went through four typical visuomotor adaptation phases (Baseline, Adaptation, After-Effect, Refresher). Gas treatment (flow rate 5 L/min) was only administered during the Adaptation phase of the visuomotor experiment, in both groups. The NbOxTr provided during the Adaptation phase led to significantly faster and about 30% improved learning (p < 0.05). Notably, these motor learning improvements consolidated into the subsequent experiment phases, i.e., after the gas treatment was terminated (p < 0.05). We conclude that this simple and brief NbOxTr dramatically improved fundamental human motor learning processes and may provide promising potential for neurorehabilitation and skill-learning approaches. Further studies should investigate whether similar improvements exist in elderly and neurologically impaired individuals, other motor learning tasks, and also long-lasting effects.

The application of machine learning to air pollution research: A bibliometric analysis

Machine learning (ML) is an advanced computer algorithm that simulates the human learning process to solve problems. With an explosion of monitoring data and the increasing demand for fast and accurate prediction, ML models have been rapidly developed and applied in air pollution research. In order to explore the status of ML applications in air pollution research, a bibliometric analysis was made based on 2962 articles published from 1990 to 2021. The number of publications increased sharply after 2017, comprising approximately 75% of the total. Institutions in China and United States contributed half of all publications with most research being conducted by individual groups rather than global collaborations. Cluster analysis revealed four main research topics for the application of ML: chemical characterization of pollutants, short-term forecasting, detection improvement and optimizing emission control. The rapid development of ML algorithms has increased the capability to explore the chemical characteristics of multiple pollutants, analyze chemical reactions and their driving factors, and simulate scenarios. Combined with multi-field data, ML models are a powerful tool for analyzing atmospheric chemical processes and evaluating the management of air quality and deserve greater attention in future.

Encompassing Embodiment in Entrepreneurial Learning

Abstract The present conceptual article discusses non-cognitive aspects of entrepreneurial learning. Entrepreneurs are known to undergo extreme experience phases during establishing their firms where peak experience, peak performance and flow counteract. As a result, increasing anxiety and stress may hamper their performance. Non-cognitive skills that consider simultaneously mental processes, emotions and spirit in connection with the human neurophysiological system in a holistic, human learning process, could appear more efficient in describing how entrepreneurial learning occurs in stressful situations. In the present discussion somatic learning education is suggested as a possibility to enhance entrepreneurial learning, creativity and performance in stressful situations. As non-cognitive entrepreneurial skills have been overlooked in the extant literature, the present discussion initiates a discussion for further research in the field. The concepts of holistic entrepreneurial learning, embodiment and somatic learning are described while their relevance to stressful business start-upping and entrepreneurial well-being is sought. The article concludes with relevant research questions for further examination. Keywords: Entrepreneurial education, Embodiment, Somatics, Peak performance, Peak experience, Flow, Well-being, Stress regulation, Innovation, Creativity.

PHILNet: A novel efficient approach for time series forecasting using deep learning

Time series is one of the most common data types in the industry nowadays. Forecasting the future of a time series behavior can be useful in planning ahead, saving time, resources, and helping avoid undesired scenarios. To make the forecasting, historical data is utilized due to the causal nature of the time series. Several deep learning algorithms have been presented in this area, where the input is processed through a series of non-linear functions to produce the output. We present a novel strategy to improve the performance of deep learning models in time series forecasting in terms of efficiency while reaching similar effectiveness. This approach separates the model into levels, starting with the easiest and continuing to the most difficult. The simpler levels deal with smoothed versions of the input, whereas the most sophisticated level deals with the raw data. This strategy seeks to mimic the human learning process, in which basic tasks are completed initially, followed by more precise and sophisticated ones. Our method achieved promising results, obtaining a 35% improvement in mean squared error and a 2.6 time decrease in training time compared with the best models found in a variety of time series.

Acute ethanol exposure leads to long-term effects on memory, behavior, and transcriptional regulation in the zebrafish brain

Alcohol consumption is associated with alterations in memory and learning processes in humans and animals. In this context, research models such as the zebrafish (Danio rerio) arise as key organisms in behavioral and molecular studies that attempt to clarify alterations in the Central Nervous System (CNS), like those related to alcohol use. Accordingly, we used the zebrafish as a model to evaluate the effects of ethanol on the learning and memory process, as well as its relationship with behavior and transcriptional regulation of lrfn2, lrrk2, grin1a, and bdnf genes in the brain. To this end, for the memory and learning evaluation, we conducted the Novel Object Recognition test (NOR); for behavior, the Novel Tank test; and for gene transcription, qPCR, after 2 h, 24 h, and 8 days of ethanol exposure. As a result, we noticed in the NOR that after 8 days of ethanol exposure, the control group spent more time exploring the novel object than when compared to 2 h post-exposure, indicating that naturally zebrafish remember familiar objects. In animals in the Treatment group, however, no object recognition behavior was observed, suggesting that alcohol affected the learning and memory processes of the animals and stimulated an anxiolytic effect in them. Regarding transcriptional regulation, 24 h after alcohol exposure, we found hyper-regulation of bdnf and, after 8 days, a hypo-regulation of lrfn2 and lrrk2. To conclude, we demonstrated that ethanol exposure may have influenced learning ability and memory formation in zebrafish, as well as behavior and regulation of gene transcription. These data are relevant for further understanding the application of zebrafish in research associated with ethanol consumption and behavior.

Analogies of human speech and bird song: From vocal learning behavior to its neural basis.

Vocal learning is a complex acquired social behavior that has been found only in very few animals. The process of animal vocal learning requires the participation of sensorimotor function. By accepting external auditory input and cooperating with repeated vocal imitation practice, a stable pattern of vocal information output is eventually formed. In parallel evolutionary branches, humans and songbirds share striking similarities in vocal learning behavior. For example, their vocal learning processes involve auditory feedback, complex syntactic structures, and sensitive periods. At the same time, they have evolved the hierarchical structure of special forebrain regions related to vocal motor control and vocal learning, which are organized and closely associated to the auditory cortex. By comparing the location, function, genome, and transcriptome of vocal learning-related brain regions, it was confirmed that songbird singing and human language-related neural control pathways have certain analogy. These common characteristics make songbirds an ideal animal model for studying the neural mechanisms of vocal learning behavior. The neural process of human language learning may be explained through similar neural mechanisms, and it can provide important insights for the treatment of language disorders.

Intensive Urbanization, Urban Meteorology and Air Pollutants: Effects on the Temperature of a City in a Basin Geography.

A qualitative study of thermal transfers is carried out from a record of measurements (time series) of meteorological variables (temperature, relative humidity and magnitude of wind speeds) and pollutants (PM10, PM2.5 and CO) in six localities located at different heights in the geographic basin of Santiago de Chile. The measurements were made in two periods, 2010-2013 and 2017-2020 (a total of 2,049,336 data), the last period coinciding with a process of intense urbanization, especially high-rise construction. The measurements, in the form of hourly time series, are analyzed on the one hand according to the theory of thermal conduction discretizing the differential equation of the temporal variation in the temperature and, on the other hand, through the theory of chaos that provides the entropies (S). Both procedures demonstrate, comparatively, that the last period of intense urbanization presents an increase in thermal transfers and temperature, which affects urban meteorology and makes it more complex. As shown by the chaotic analysis, there is a faster loss of information for the period 2017-2020. The consequences of the increase in temperature on human health and learning processes are studied.

Multi-Scopic Cognitive Memory System for Continuous Gesture Learning.

With the advancement of artificial intelligence technologies in recent years, research on intelligent robots has progressed. Robots are required to understand human intentions and communicate more smoothly with humans. Since gestures can have a variety of meanings, gesture recognition is one of the essential issues in communication between robots and humans. In addition, robots need to learn new gestures as humans grow. Moreover, individual gestures vary. Because catastrophic forgetting occurs in training new data in traditional gesture recognition approaches, it is necessary to preserve the prepared data and combine it with further data to train the model from scratch. We propose a Multi-scopic Cognitive Memory System (MCMS) that mimics the lifelong learning process of humans and can continuously learn new gestures without forgetting previously learned gestures. The proposed system comprises a two-layer structure consisting of an episode memory layer and a semantic memory layer, with a topological map as its backbone. The system is designed with reference to conventional continuous learning systems in three ways: (i) using a dynamic architecture without setting the network size, (ii) adding regularization terms to constrain learning, and (iii) generating data from the network itself and performing relearning. The episode memory layer clusters the data and learns their spatiotemporal representation. The semantic memory layer generates a topological map based on task-related inputs and stores them as longer-term episode representations in the robot's memory. In addition, to alleviate catastrophic forgetting, the memory replay function can reinforce memories autonomously. The proposed system could mitigate catastrophic forgetting and perform continuous learning by using both machine learning benchmark datasets and real-world data compared to conventional methods.

Continuous Estimation of Lower Limb Joint Angles From Multi-Stream Signals Based on Knowledge Tracing

Multi-stream signals are increasingly being used in robot-assisted rehabilitation training, where the timely and accurate prediction of a patient's motor intentions is frequently required to provide simultaneous and proportional control strategies. However, existing methods for motion intent prediction typically isolate signals from different modalities, resulting in a loss of signal traceability and interpretability. Therefore, we propose a multi-stream signal-fusion strategy based on knowledge tracing (MSKT). First, we collected surface electromyography, force myography, and vibroarthrography signals from the lower extremity and used different encoders to map these signals into a problem component, concept component, and identity token component. The process of human learning was then simulated using a knowledge-tracing strategy to reconstruct these components into new features. Finally, the reconstructed set of depth features was mapped to joint angles. We validated the performance of the proposed method using motion data from eight participants in different locomotion modes and compared the results to those of a temporal convolution network and long short-term memory networks. The results indicate that the MSKT achieves the lowest root-mean-squared error. This study demonstrates that the proposed knowledge-tracing-based strategy enables accurate continuous estimation for lower-limb exoskeleton rehabilitation robots.

Learn to Grasp Via Intention Discovery and Its Application to Challenging Clutter

Humans excel in grasping objects through diverse and robust policies, many of which are so probabilistically rare that exploration-based learning methods hardly observe and learn. Inspired by the human learning process, we propose a method to extract and exploit latent intents from demonstrations, and then learn diverse and robust grasping policies through self-exploration. The resulting policy can grasp challenging objects in various environments with an off-the-shelf parallel gripper. The key component is a learned intention estimator, which maps gripper pose and visual sensory to a set of sub-intents covering important phases of the grasping movement. Sub-intents can be used to build an intrinsic reward to guide policy learning. The learned policy demonstrates remarkable zero-shot generalization from simulation to the real world while retaining its robustness against states that have never been encountered during training, novel objects such as protractors and user manuals, and environments such as the cluttered conveyor.

An educational experience in ancient Rome to evaluate the impact of virtual reality on human learning processes

Immersive Virtual Reality technology has recently gained significant attention and is expanding its applications to various fields. It also has many advantages in education, as it allows to both simplify the explanation of complex topics through their visualization, and explore lost or unreachable environments. To evaluate the impact of immersive experiences on learning outcomes we developed an educational experience that lets users visit an ancient Roman Domus and provides information about daily life in Roman times. We designed a between-subjects data collection to investigate learning ratio, user experience, and cybersickness of participants through anonymous questionnaires. We collected 76 responses of participants (18–35 y.o.) divided into three conditions: a Immersive Virtual Reality experience, a slide-based lecture and a 2D desktop-based experience. Our results show that the virtual reality experience is considered more engaging and as effective as more traditional 2D and slide-based experiences in terms of learning.

Brain Communication: A system where to investigate and re-engineer human communication and learning processes.

A method for detecting and monitoring the long-term time course of brain processes is described for two different conditions: i) A abbreviated version of a visual problem-solving IQ (Intelligent Quotient) Raven test and ii) A perceptual video task consisting of watching a sequence of (3 minutes each) 5 movie genera: animation, war, romance, violence and thriller. The method consisted of the analysis of the grayscale pixel values of the spectrographic image, generated by a Fast Fourier Transform (FFT), applied over the amplitude v/s time domain of the electroencephalographic (EEG) signal recorded during the execution of the test/task.Results show a high-resolution tool for detecting and monitoring brain signals in very narrow frequency range (0,05 Hz) and time (100 ms). Subject-dependent individual differences (N=5) are evident and a number up to 10 frequency communication channels can be detected in narrow frequency range of 0,5 Hz. Combining both aspects of these tool, high resolution of the frequency range, and the subject-dependent individual differences found in the execution of the test/task, we plan to use this information to classify subjects according problem-solving and perceptual brain processing differences and learning preferences.

Active learning based sampling for high-dimensional nonlinear partial differential equations

The deep-learning-based least squares method has shown successful results in solving high-dimensional and non-linear partial differential equations (PDEs). However, this method usually converges slowly. To speed up the convergence of this approach, an active-learning-based sampling algorithm is proposed in this paper. This algorithm actively chooses the most informative training samples from a probability density function based on residual errors to facilitate error reduction. In particular, points with larger residual errors will have more chances of being selected for training. This algorithm imitates the human learning process: learners are likely to spend more time repeatedly studying mistakes than other tasks they have correctly finished. A series of numerical results are illustrated to demonstrate the effectiveness of our active-learning-based sampling in high dimensions to speed up the convergence of the deep-learning-based least squares method.

Point Adversarial Self-Mining: A Simple Method for Facial Expression Recognition.

In this article, we propose a simple yet effective approach, called point adversarial self mining (PASM), to improve the recognition accuracy in facial expression recognition (FER). Unlike previous works focusing on designing specific architectures or loss functions to solve this problem, PASM boosts the network capability by simulating human learning processes: providing updated learning materials and guidance from more capable teachers. Specifically, to generate new learning materials, PASM leverages a point adversarial attack method and a trained teacher network to locate the most informative position related to the target task, generating harder learning samples to refine the network. The searched position is highly adaptive since it considers both the statistical information of each sample and the teacher network capability. Other than being provided new learning materials, the student network also receives guidance from the teacher network. After the student network finishes training, the student network changes its role and acts as a teacher, generating new learning materials and providing stronger guidance to train a better student network. The adaptive learning materials generation and teacher/student update can be conducted more than one time, improving the network capability iteratively. Extensive experimental results validate the efficacy of our method over the existing state of the arts for FER.

Ensemble Self-Paced Learning Based on Adaptive Mixture Weighting

Self-paced learning (SPL) is a learning mechanism inspired by human and animal learning processes that gives variable weights to samples, gradually introducing simple to more complicated samples into the learning set as the “age” parameter increases. To regulate the learning process, a self-paced weighting regularization term with an “age” parameter is introduced to the learning function. Several self-paced weighting methods have been proposed, and different regularization terms might result in varied learning performance. However, on the one hand, it is difficult to select a suitable weighting method for SPL. On the other hand, it is challenging to determine the “age” parameter, and it is easy for SPL to obtain poor results as the “age” of the model increases. To solve the aforementioned difficulties, an ensemble SPL approach with an adaptive mixture weighting mechanism is proposed in this study. First, as the “age” parameter increases, a set of base classifiers is collected to produce a new data set, which is used to learn the second-level classifier. Then, the ensemble model is used to generate the final output to avoid the selection of the optimal “age” parameter. An adaptive mixture weighting method is designed to reduce the dependence of parameters on human experience. The previous methods find it difficult to determine the “age” parameters or self-paced parameters. In this paper, these parameters can be adjusted adaptively during the learning process. In comparison with the previous SPL techniques, the proposed method achieves the best results in 27 of the 32 datasets in the experiments with the adaptive parameters. The statistical tests are carried out to show that the proposed method is superior to other state-of-the-art algorithms.

A physics-oriented memristor model with the coexistence of NDR effect and RS memory behavior for bio-inspired computing

Bio-inspired computing promises fundamentally different ways to advances in artificial intelligence with extreme energy efficiency. Memristive technologies due to the non-volatility, high density, low-power, and synaptic bionic properties can help in realizing bio-inspired architecture and its hardware implementation. This paper proposes a novel physics-oriented memristor model with coexistence of negative differential resistance (NDR) effect and resistive switching (RS) memory behavior for bio-inspired computing. Firstly, an Ag/TiOx/FTO memristor is fabricated using sol-gel and magnetron sputtering method, and its performance test demonstrates that the coexistence of NDR effect and RS memory behavior can be modulated by the moisture. Then, a physical-oriented memristor model is constructed, which provides the possibility to explore the dynamics of the coexistence of NDR effect and RS memory behavior in simulation. Furthermore, a memristor-based affective computing circuit emulating the process of human affective associative learning is designed. The experiment demonstrates that the coexistence of NDR effect and RS memory behavior can change the memory time without additional circuit and cost, which is expected to realize the automatic conversion from short-term memory to long-term memory in bio-inspired computing.

Unambiguous Identification of Objects in Different Environments and Conditions Based on Holographic Machine Learning Algorithms

Unambiguous provision of results in different environments and conditions by machine learning algorithms is an unresolved problem until now. Solving the problem of machine learning with unambiguous provision of results in different environments and conditions can be approached by focusing on the psychophysical holographic process of human learning. A person, with a mental concentration of attention, experimentally teaches vision, hearing, psyche and mind in a holographic way and in a resonant way to perceive, recognize and recognize phenomena, processes, objects, subjects, meanings, music and other entities in various environments and conditions. A person experimentally teaches the psyche and feelings to rationally navigate in various environments and conditions. Holographic algorithms of experienced machine learning will help neural network ensembles to unambiguously recognize objects, subjects, music, texts in various environments and conditions using a model of recognizing their own or someone else's. Machine learning simulates holographic processes of human communication memorization of entities. Searching for objects in different environments in different conditions based on experienced machine learning simulates resonant associative processes of human entity detection. By simulating holographic processes of the human psyche based on artificial intelligence of machine learning with Fourier transformation, using full parametric sequences of necessary and sufficient data of holograms of target objects, it is possible to solve the problem of their unambiguous detection in different environments and in different conditions.

Machine learning for energy-resource allocation, workflow scheduling and live migration in cloud computing: State-of-the-art survey

Machine learning and artificial intelligence techniques have been proven helpful when pragmatic to a wide range of complex problems and areas such as energy optimization, workflow scheduling, video gaming, and cloud computing. When machine learning and cloud computing algorithms are combined, they help achieve better outcomes by providing the improved performance of cloud data centers compared to solutions currently employed by various researchers. It is also helpful for migrating the virtual machines based on the current traffic condition and fluctuation due to network congestion and bandwidth availability. The survey aims to present the improvement in dynamic load allocation, task scheduling, energy optimization, live migration, mobile cloud computing, and security on the cloud using machine learning classification. Machine learning algorithms are prevailing analytical approaches that allow machines to identify patterns and simplify the human learning process. The flow of the paper consists of an introduction part, motivation, and background study, including a framework for cloud-machine learning integration, best practices of introducing machine learning in cloud computing, and the objective of the work. The paper also highlights the machine learning-based cloud services and the role of artificial intelligence in different cloud computing platforms. This comprehensive study provides mindfulness and valuable facilities to the researchers by giving thorough studies about various machine learning algorithms and their applicability in cloud computing.

HASAN LANGGULUNG PARADIGM ABOUT APPRECIATION OF ISLAMIC VALUES IN EDUCATION

Islamic values ??are something that is valuable for the effort that has been given, which has advantages and can be compared with something else. Islamic values ??as a driving force that is inherent in a person's soul so that it becomes a way of life. The pattern of human behavior must follow Islamic values ??accompanied by appreciation in the human being so that certain thoughts, attitudes, and feelings will develop. This study aims to examine more deeply Hasan Langgulung's paradigm of appreciation of Islamic values ??in education. This research uses library research method with descriptive, conceptual, and psychological approaches. The results of this study indicate: appreciation of Islamic values ??is a type of human learning process in life, by following the law in the learning process without violating existing rules. The appreciation of Islamic values ??in oneself is accompanied by a learning process in the presence of a stimulus from humans to practice Islamic values ??in education and various certain values ??so that these actions will be rewarded from human practice. If Islamic values ??have become human guidelines, if the human does not live it in the form of practice, then the human will feel uncomfortable in his life.