Search

As the demand for Internet access increases, malicious traffic on the Internet has soared also. In view of the fact that the existing malicious-traffic-identification methods suffer from low accuracy, this paper proposes a malicious-traffic-identification method based on contrastive learning. The proposed method is able to overcome the shortcomings of traditional methods that rely on labeled samples and is able to learn data feature representations carrying semantic information from unlabeled data, thus improving the model accuracy. In this paper, a new malicious traffic feature extraction model based on a Transformer is proposed. Employing a self-attention mechanism, the proposed feature extraction model can extract the bytes features of malicious traffic by performing calculations on the malicious traffic, thereby realizing the efficient identification of malicious traffic. In addition, a bidirectional GLSTM is introduced to extract the timing features of malicious traffic. The experimental results show that the proposed method is superior to the latest published methods in terms of accuracy and F1 score. [ABSTRACT FROM AUTHOR]

Machine learning-based controllers of prostheses using electromyographic signals have become very popular in the last decade. The regression approach allows a simultaneous and proportional control of the intended movement in a more natural way than the classification approach, where the number of movements is discrete by definition. However, it is not common to find regression-based controllers working for more than two degrees of freedom at the same time. In this paper, we present the application of the adaptive linear regressor in a relatively low-dimensional feature space with only eight sensors to the problem of a simultaneous and proportional control of three degrees of freedom (left–right, up–down and open–close hand movements). We show that a key element usually overlooked in the learning process of the regressor is the training paradigm. We propose a closed-loop procedure, where the human learns how to improve the quality of the generated EMG signals, helping also to obtain a better controller. We apply it to 10 healthy and 3 limb-deficient subjects. Results show that the combination of the multidimensional targets and the open-loop training protocol significantly improve the performance, increasing the average completion rate from 53% to 65% for the most complicated case of simultaneously controlling the three degrees of freedom. [ABSTRACT FROM AUTHOR]

In this paper, we propose a learning state evaluation method based on face detection and head pose estimation. This method is suitable for mobile devices with weak computing power, so it is necessary to control the parameter quantity of the face detection and head pose estimation network. Firstly, we propose a ghost and attention module (GA) base face detection network (GA-Face). GA-Face reduces the number of parameters and computation in the feature extraction network through the ghost module, and focuses the network on important features through a parameter-free attention mechanism. We also propose a lightweight dual-branch (DB) head pose estimation network: DB-Net. Finally, we propose a student learning state evaluation algorithm. This algorithm can evaluate the learning status of students based on the distance between their faces and the screen, as well as their head posture. We validate the effectiveness of the proposed GA-Face and DB-Net on several standard face detection datasets and standard head pose estimation datasets. Finally, we validate, through practical cases, that the proposed online learning state assessment method can effectively assess the level of student attention and concentration, and, due to its low computational complexity, will not interfere with the student's learning process. [ABSTRACT FROM AUTHOR]

Human action recognition has drawn significant attention because of its importance in computer vision-based applications. Action recognition based on skeleton sequences has rapidly advanced in the last decade. Conventional deep learning-based approaches are based on extracting skeleton sequences through convolutional operations. Most of these architectures are implemented by learning spatial and temporal features through multiple streams. These studies have enlightened the action recognition endeavor from various algorithmic angles. However, three common issues are observed: (1) The models are usually complicated; therefore, they have a correspondingly higher computational complexity. (2) For supervised learning models, the reliance on labels during training is always a drawback. (3) Implementing large models is not beneficial to real-time applications. To address the above issues, in this paper, we propose a multi-layer perceptron (MLP)-based self-supervised learning framework with a contrastive learning loss function (ConMLP). ConMLP does not require a massive computational setup; it can effectively reduce the consumption of computational resources. Compared with supervised learning frameworks, ConMLP is friendly to the huge amount of unlabeled training data. In addition, it has low requirements for system configuration and is more conducive to being embedded in real-world applications. Extensive experiments show that ConMLP achieves the top one inference result of 96.9% on the NTU RGB+D dataset. This accuracy is higher than the state-of-the-art self-supervised learning method. Meanwhile, ConMLP is also evaluated in a supervised learning manner, which has achieved comparable performance to the state of the art of recognition accuracy. [ABSTRACT FROM AUTHOR]

Recently, deep learning has been widely used to solve existing computing problems through large-scale data mining. Conventional training of the deep learning model is performed on a central (cloud) server that is equipped with high computing power, by integrating data via high computational intensity. However, integrating raw data from multiple clients raises privacy concerns that are increasingly being focused on. In federated learning (FL), clients train deep learning models in a distributed fashion using their local data; instead of sending raw data to a central server, they send parameter values of the trained local model to a central server for integration. Because FL does not transmit raw data to the outside, it is free from privacy issues. In this paper, we perform an experimental study that explores the dynamics of the FL-based Android malicious app detection method under three data distributions across clients, i.e., (i) independent and identically distributed (IID), (ii) non-IID, (iii) non-IID and unbalanced. Our experiments demonstrate that the application of FL is feasible and efficient in detecting malicious Android apps in a distributed manner on cellular networks. [ABSTRACT FROM AUTHOR]

A robust and scientifically grounded teaching evaluation system holds significant importance in modern education, serving as a crucial metric that reflects the quality of classroom instruction. However, current methodologies within smart classroom environments have distinct limitations. These include accommodating a substantial student population, grappling with object detection challenges due to obstructions, and encountering accuracy issues in recognition stemming from varying observation angles. To address these limitations, this paper proposes an innovative data augmentation approach designed to detect distinct student behaviors by leveraging focused behavioral attributes. The primary objective is to alleviate the pedagogical workload. The process begins with assembling a concise dataset tailored for discerning student learning behaviors, followed by the application of data augmentation techniques to significantly expand its size. Additionally, the architectural prowess of the Extended-efficient Layer Aggregation Networks (E-ELAN) is harnessed to effectively extract a diverse array of learning behavior features. Of particular note is the integration of the Channel-wise Attention Module (CBAM) focal mechanism into the feature detection network. This integration plays a pivotal role, enhancing the network's ability to detect key cues relevant to student learning behaviors and thereby heightening feature identification precision. The culmination of this methodological journey involves the classification of the extracted features through a dual-pronged conduit: the Feature Pyramid Network (FPN) and the Path Aggregation Network (PAN). Empirical evidence vividly demonstrates the potency of the proposed methodology, yielding a mean average precision (mAP) of 96.7%. This achievement surpasses comparable methodologies by a substantial margin of at least 11.9%, conclusively highlighting the method's superior recognition capabilities. This research has an important impact on the field of teaching evaluation system, which helps to reduce the burden of educators on the one hand, and makes teaching evaluation more objective and accurate on the other hand. [ABSTRACT FROM AUTHOR]

As an important component of the railway system, the surface damage that occurs on the rails due to daily operations can pose significant safety hazards. This paper proposes a simple yet effective rail surface defect detection model, FS-RSDD, for rail surface condition monitoring, which also aims to address the issue of insufficient defect samples faced by previous detection models. The model utilizes a pre-trained model to extract deep features of both normal rail samples and defect samples. Subsequently, an unsupervised learning method is employed to learn feature distributions and obtain a feature prototype memory bank. Using prototype learning techniques, FS-RSDD estimates the probability of a test sample belonging to a defect at each pixel based on the prototype memory bank. This approach overcomes the limitations of deep learning algorithms based on supervised learning techniques, which often suffer from insufficient training samples and low credibility in validation. FS-RSDD achieves high accuracy in defect detection and localization with only a small number of defect samples used for training. Surpassing benchmarked few-shot industrial defect detection algorithms, FS-RSDD achieves an ROC of 95.2% and 99.1% on RSDDS Type-I and Type-II rail defect data, respectively, and is on par with state-of-the-art unsupervised anomaly detection algorithms. [ABSTRACT FROM AUTHOR]

In a society centered on hyper-connectivity, information sharing is crucial, but it must be ensured that each piece of information is viewed only by legitimate users; for this purpose, the medium that connects information and users must be able to identify illegal users. In this paper, we propose a smartphone authentication system based on human gait, breaking away from the traditional authentication method of using the smartphone as the medium. After learning human gait features with a convolutional neural network deep learning model, it is mounted on a smartphone to determine whether the user is a legitimate user by walking for 1.8 s while carrying the smartphone. The accuracy, precision, recall, and F1-score were measured as evaluation indicators of the proposed model. These measures all achieved an average of at least 90%. The analysis results show that the proposed system has high reliability. Therefore, this study demonstrates the possibility of using human gait as a new user authentication method. In addition, compared to our previous studies, the gait data collection time for user authentication of the proposed model was reduced from 7 to 1.8 s. This reduction signifies an approximately four-fold performance enhancement through the implementation of filtering techniques and confirms that gait data collected over a short period of time can be used for user authentication. [ABSTRACT FROM AUTHOR]

Getting stuck is an inevitable part of learning programming. Long-term stuck decreases the learner's motivation and learning efficiency. The current approach to supporting learning in lectures involves teachers finding students who are getting stuck, reviewing their source code, and solving the problems. However, it is difficult for teachers to grasp every learner's stuck situation and to distinguish stuck or deep thinking only by their source code. Teachers should advise learners only when there is no progress and they are psychologically stuck. This paper proposes a method for detecting when learners get stuck during programming by using multi-modal data, considering both their source code and psychological state measured by a heart rate sensor. The evaluation results of the proposed method show that it can detect more stuck situations than the method that uses only a single indicator. Furthermore, we implemented a system that aggregates the stuck situation detected by the proposed method and presents them to a teacher. In evaluations during the actual programming lecture, participants rated the notification timing of application as suitable and commented that the application was useful. The questionnaire survey showed that the application can detect situations where learners cannot find solutions to exercise problems or express them in programming. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is an important research problem in computer vision. This problem is widely applied to building applications in human–machine interactions, monitoring, etc. Especially, HAR based on the human skeleton creates intuitive applications. Therefore, determining the current results of these studies is very important in selecting solutions and developing commercial products. In this paper, we perform a full survey on using deep learning to recognize human activity based on three-dimensional (3D) human skeleton data as input. Our research is based on four types of deep learning networks for activity recognition based on extracted feature vectors: Recurrent Neural Network (RNN) using extracted activity sequence features; Convolutional Neural Network (CNN) uses feature vectors extracted based on the projection of the skeleton into the image space; Graph Convolution Network (GCN) uses features extracted from the skeleton graph and the temporal–spatial function of the skeleton; Hybrid Deep Neural Network (Hybrid–DNN) uses many other types of features in combination. Our survey research is fully implemented from models, databases, metrics, and results from 2019 to March 2023, and they are presented in ascending order of time. In particular, we also carried out a comparative study on HAR based on a 3D human skeleton on the KLHA3D 102 and KLYOGA3D datasets. At the same time, we performed analysis and discussed the obtained results when applying CNN-based, GCN-based, and Hybrid–DNN-based deep learning networks. [ABSTRACT FROM AUTHOR]

One of the challenges of spatial cognition, such as self-localization and navigation, is to develop an efficient learning approach capable of mimicking human ability. This paper proposes a novel approach for topological geolocalization on the map using motion trajectory and graph neural networks. Specifically, our learning method learns an embedding of the motion trajectory encoded as a path subgraph where the node and edge represent turning direction and relative distance information by training a graph neural network. We formulate the subgraph learning as a multi-class classification problem in which the output node IDs are interpreted as the object's location on the map. After training using three map datasets with small, medium, and large sizes, the node localization tests on simulated trajectories generated from the map show 93.61%, 95.33%, and 87.50% accuracy, respectively. We also demonstrate similar accuracy for our approach on actual trajectories generated by visual-inertial odometry. The key benefits of our approach are as follows: (1) we take advantage of the powerful graph-modeling ability of neural graph networks, (2) it only requires a map in the form of a 2D graph, and (3) it only requires an affordable sensor that generates relative motion trajectory. [ABSTRACT FROM AUTHOR]

Changes in pig behavior are crucial information in the livestock breeding process, and automatic pig behavior recognition is a vital method for improving pig welfare. However, most methods for pig behavior recognition rely on human observation and deep learning. Human observation is often time-consuming and labor-intensive, while deep learning models with a large number of parameters can result in slow training times and low efficiency. To address these issues, this paper proposes a novel deep mutual learning enhanced two-stream pig behavior recognition approach. The proposed model consists of two mutual learning networks, which include the red–green–blue color model (RGB) and flow streams. Additionally, each branch contains two student networks that learn collaboratively to effectively achieve robust and rich appearance or motion features, ultimately leading to improved recognition performance of pig behaviors. Finally, the results of RGB and flow branches are weighted and fused to further improve the performance of pig behavior recognition. Experimental results demonstrate the effectiveness of the proposed model, which achieves state-of-the-art recognition performance with an accuracy of 96.52%, surpassing other models by 2.71%. [ABSTRACT FROM AUTHOR]

Blind image quality assessment (BIQA) aims to evaluate image quality in a way that closely matches human perception. To achieve this goal, the strengths of deep learning and the characteristics of the human visual system (HVS) can be combined. In this paper, inspired by the ventral pathway and the dorsal pathway of the HVS, a dual-pathway convolutional neural network is proposed for BIQA tasks. The proposed method consists of two pathways: the "what" pathway, which mimics the ventral pathway of the HVS to extract the content features of distorted images, and the "where" pathway, which mimics the dorsal pathway of the HVS to extract the global shape features of distorted images. Then, the features from the two pathways are fused and mapped to an image quality score. Additionally, gradient images weighted by contrast sensitivity are used as the input to the "where" pathway, allowing it to extract global shape features that are more sensitive to human perception. Moreover, a dual-pathway multi-scale feature fusion module is designed to fuse the multi-scale features of the two pathways, enabling the model to capture both global features and local details, thus improving the overall performance of the model. Experiments conducted on six databases show that the proposed method achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

In recent years, the rapid development of deep learning approaches has paved the way to explore the underlying factors that explain the data. In particular, several methods have been proposed to learn to identify and disentangle these underlying explanatory factors in order to improve the learning process and model generalization. However, extracting this representation with little or no supervision remains a key challenge in machine learning. In this paper, we provide a theoretical outlook on recent advances in the field of unsupervised representation learning with a focus on auto-encoding-based approaches and on the most well-known supervised disentanglement metrics. We cover the current state-of-the-art methods for learning disentangled representation in an unsupervised manner while pointing out the connection between each method and its added value on disentanglement. Further, we discuss how to quantify disentanglement and present an in-depth analysis of associated metrics. We conclude by carrying out a comparative evaluation of these metrics according to three criteria, (i) modularity, (ii) compactness and (iii) informativeness. Finally, we show that only the Mutual Information Gap score (MIG) meets all three criteria. [ABSTRACT FROM AUTHOR]

Health assessment and remaining useful life prediction are usually seen as separate tasks in industrial systems. Some multitask models use common features to handle these tasks synchronously, but they lack the usage of the representation in different scales and time-frequency domain. A lack of balance also exists among these scales. Therefore, a gated multiscale multitask learning model known as GMM-Net is proposed in this paper. By using the time-frequency representation, GMM-Net can obtain features of different scales via different kernels and compose the features by a gating network. A detailed loss function whose weight can be searched in a smaller scale is designed. The model is tested with different weights in the total loss function, and an optimal weight is found. Using this optimal weight, it is observed that the proposed method converges to a smaller loss and has a smaller model size than long short-term memory (LSTM) and gated recurrent unit (GRU) with less training time. The experiment results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Recently, deep learning has become more and more extensive in the field of fault diagnosis. However, most deep learning methods rely on large amounts of labeled data to train the model, which leads to their poor generalized ability in the application of different scenarios. To overcome this deficiency, this paper proposes a novel generalized model based on self-supervised learning and sparse filtering (GSLSF). The proposed method includes two stages. Firstly (1), considering the representation of samples on fault and working condition information, designing self-supervised learning pretext tasks and pseudo-labels, and establishing a pre-trained model based on sparse filtering. Secondly (2), a knowledge transfer mechanism from the pre-training model to the target task is established, the fault features of the deep representation are extracted based on the sparse filtering model, and softmax regression is applied to distinguish the type of failure. This method can observably enhance the model's diagnostic performance and generalization ability with limited training data. The validity of the method is proved by the fault diagnosis results of two bearing datasets. [ABSTRACT FROM AUTHOR]

The ability to measure students' engagement in an educational setting may facilitate timely intervention in both the learning and the teaching process in a variety of classroom settings. In this paper, a real-time automatic student engagement measure is proposed through investigating two of the main components of engagement: the behavioral engagement and the emotional engagement. A biometric sensor network (BSN) consisting of web cameras, a wall-mounted camera and a high-performance computing machine was designed to capture students' head poses, eye gaze, body movements, and facial emotions. These low-level features are used to train an AI-based model to estimate the behavioral and emotional engagement in the class environment. A set of experiments was conducted to compare the proposed technology with the state-of-the-art frameworks. The proposed framework shows better accuracy in estimating both behavioral and emotional engagement. In addition, it offers superior flexibility to work in any educational environment. Further, this approach allows a quantitative comparison of teaching methods. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of achieving lifelong open-ended learning autonomy in robotics, and how different cognitive architectures provide functionalities that support it. To this end, we analyze a set of well-known cognitive architectures in the literature considering the different components they address and how they implement them. Among the main functionalities that are taken as relevant for lifelong open-ended learning autonomy are the fact that architectures must contemplate learning, and the availability of contextual memory systems, motivations or attention. Additionally, we try to establish which of them were actually applied to real robot scenarios. It transpires that in their current form, none of them are completely ready to address this challenge, but some of them do provide some indications on the paths to follow in some of the aspects they contemplate. It can be gleaned that for lifelong open-ended learning autonomy, motivational systems that allow finding domain-dependent goals from general internal drives, contextual long-term memory systems that all allow for associative learning and retrieval of knowledge, and robust learning systems would be the main components required. Nevertheless, other components, such as attention mechanisms or representation management systems, would greatly facilitate operation in complex domains. [ABSTRACT FROM AUTHOR]

Federated learning has a distributed collaborative training mode, widely used in IoT scenarios of edge computing intelligent services. However, federated learning is vulnerable to malicious attacks, mainly backdoor attacks. Once an edge node implements a backdoor attack, the embedded backdoor mode will rapidly expand to all relevant edge nodes, which poses a considerable challenge to security-sensitive edge computing intelligent services. In the traditional edge collaborative backdoor defense method, only the cloud server is trusted by default. However, edge computing intelligent services have limited bandwidth and unstable network connections, which make it impossible for edge devices to retrain their models or update the global model. Therefore, it is crucial to detect whether the data of edge nodes are polluted in time. This paper proposes a layered defense framework for edge-computing intelligent services. At the edge, we combine the gradient rising strategy and attention self-distillation mechanism to maximize the correlation between edge device data and edge object categories and train a clean model as much as possible. On the server side, we first implement a two-layer backdoor detection mechanism to eliminate backdoor updates and use the attention self-distillation mechanism to restore the model performance. Our results show that the two-stage defense mode is more suitable for the security protection of edge computing intelligent services. It can not only weaken the effectiveness of the backdoor at the edge end but also conduct this defense at the server end, making the model more secure. The precision of our model on the main task is almost the same as that of the clean model. [ABSTRACT FROM AUTHOR]

This paper proposes to use deep reinforcement learning to teach a physics-based human musculoskeletal model to ascend stairs and ramps. The deep reinforcement learning architecture employs the proximal policy optimization algorithm combined with imitation learning and is trained with experimental data of a public dataset. The human model is developed in the open-source simulation software OpenSim, together with two objects (i.e., the stairs and ramp) and the elastic foundation contact dynamics. The model can learn to ascend stairs and ramps with muscle forces comparable to healthy subjects and with a forward dynamics comparable to the experimental training data, achieving an average correlation of 0.82 during stair ascent and of 0.58 during ramp ascent across both the knee and ankle joints. [ABSTRACT FROM AUTHOR]

Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets. [ABSTRACT FROM AUTHOR]

Doppler-radar-based continuous human motion recognition recently has attracted extensive attention, which is a favorable choice for privacy and personal security. Existing results of continuous human motion recognition (CHMR) using mmWave FMCW Radar are not considered the continuous human motion with the high similarity problem. In this paper, we proposed a new CHMR algorithm with the consideration of the high similarity (HS) problem, called as CHMR-HS, by using the modified Transformer-based learning model. As far as we know, this is the first result in the literature to investigate the continuous HMR with the high similarity. To obtain the clear FMCW radar images, the background and target signals of the detected human are separated through the background denoising and the target extraction algorithms. To investigate the effects of the spectral-temporal multi-features with different dimensions, Doppler, range, and angle signatures are extracted as the 2D features and range-Doppler-time and range-angle-time signatures are extracted as the 3D features. The 2D/3D features are trained into the adjusted Transformer-encoder model to distinguish the difference of the high-similarity human motions. The conventional Transformer-decoder model is also re-designed to be Transformer-sequential-decoder model such that Transformer-sequential-decoder model can successfully recognize the continuous human motions with the high similarity. The experimental results show that the accuracy of our proposed CHMR-HS scheme are 95.2% and 94.5% if using 3D and 2D features, the simulation results also illustrates that our CHMR-HS scheme has advantages over existing CHMR schemes. [ABSTRACT FROM AUTHOR]

Wearable sensors have traditionally been used to measure and monitor vital human signs for well-being and healthcare applications. However, there is a growing interest in using and deploying these technologies to facilitate teaching and learning, particularly in a higher education environment. The aim of this paper is therefore to systematically review the range of wearable devices that have been used for enhancing the teaching and delivery of engineering curricula in higher education. Moreover, we compare the advantages and disadvantages of these devices according to the location in which they are worn on the human body. According to our survey, wearable devices for enhanced learning have mainly been worn on the head (e.g., eyeglasses), wrist (e.g., watches) and chest (e.g., electrocardiogram patch). In fact, among those locations, head-worn devices enable better student engagement with the learning materials, improved student attention as well as higher spatial and visual awareness. We identify the research questions and discuss the research inclusion and exclusion criteria to present the challenges faced by researchers in implementing learning technologies for enhanced engineering education. Furthermore, we provide recommendations on using wearable devices to improve the teaching and learning of engineering courses in higher education. [ABSTRACT FROM AUTHOR]

Compared with the fixed fusion structure, the flexible fusion structure with mixed fusion methods has better adjustment performance for the complex air task network systems, and it can effectively help the system to achieve the goal under the given constraints. Because of the time-varying situation of the task network system induced by moving nodes and non-cooperative target, and limitations such as communication bandwidth and measurement distance, it is necessary to dynamically adjust the system fusion structure including sensors and fusion methods in a given adjustment period. Aiming at this, this paper studies the design of a flexible fusion algorithm by using an optimization learning technology. The purpose is to dynamically determine the sensors' numbers and the associated sensors to take part in the centralized and distributed fusion processes, respectively, herein termed sensor subsets selection. Firstly, two system performance indexes are introduced. Especially, the survivability index is presented and defined. Secondly, based on the two indexes and considering other conditions such as communication bandwidth and measurement distance, optimization models for both single target tracking and multi-target tracking are established. Correspondingly, solution steps are given for the two optimization models in detail. Simulation examples are demonstrated to validate the proposed algorithms. [ABSTRACT FROM AUTHOR]

Most facial analysis methods perform well in standardized testing but not in real-world testing. The main reason is that training models cannot easily learn various human features and background noise, especially for facial landmark detection and head pose estimation tasks with limited and noisy training datasets. To alleviate the gap between standardized and real-world testing, we propose a pseudo-labeling technique using a face recognition dataset consisting of various people and background noise. The use of our pseudo-labeled training dataset can help to overcome the lack of diversity among the people in the dataset. Our integrated framework is constructed using complementary multitask learning methods to extract robust features for each task. Furthermore, introducing pseudo-labeling and multitask learning improves the face recognition performance by enabling the learning of pose-invariant features. Our method achieves state-of-the-art (SOTA) or near-SOTA performance on the AFLW2000-3D and BIWI datasets for facial landmark detection and head pose estimation, with competitive face verification performance on the IJB-C test dataset for face recognition. We demonstrate this through a novel testing methodology that categorizes cases as soft, medium, and hard based on the pose values of IJB-C. The proposed method achieves stable performance even when the dataset lacks diverse face identifications. [ABSTRACT FROM AUTHOR]

Human motion capture technology, which leverages sensors to track the movement trajectories of key skeleton points, has been progressively transitioning from industrial applications to broader civilian applications in recent years. It finds extensive use in fields such as game development, digital human modeling, and sport science. However, the affordability of these sensors often compromises the accuracy of motion data. Low-cost motion capture methods often lead to errors in the captured motion data. We introduce a novel approach for human motion reconstruction and enhancement using spatio-temporal attention-based graph convolutional networks (ST-ATGCNs), which efficiently learn the human skeleton structure and the motion logic without requiring prior human kinematic knowledge. This method enables unsupervised motion data restoration and significantly reduces the costs associated with obtaining precise motion capture data. Our experiments, conducted on two extensive motion datasets and with real motion capture sensors such as the SONY (Tokyo, Japan) mocopi, demonstrate the method's effectiveness in enhancing the quality of low-precision motion capture data. The experiments indicate the ST-ATGCN's potential to improve both the accessibility and accuracy of motion capture technology. [ABSTRACT FROM AUTHOR]

In this paper, a novel random facial variation modeling system for sparse representation face recognition is presented. Although recently Sparse Representation-Based Classification (SRC) has represented a breakthrough in the field of face recognition due to its good performance and robustness, there is the critical problem that SRC needs sufficiently large training samples to achieve good performance. To address these issues, we challenge the single-sample face recognition problem with intra-class differences of variation in a facial image model based on random projection and sparse representation. In this paper, we present a developed facial variation modeling systems composed only of various facial variations. We further propose a novel facial random noise dictionary learning method that is invariant to different faces. The experiment results on the AR, Yale B, Extended Yale B, MIT and FEI databases validate that our method leads to substantial improvements, particularly in single-sample face recognition problems. [ABSTRACT FROM AUTHOR]

Development of distributed Multi-Agent Reinforcement Learning (MARL) algorithms has attracted an increasing surge of interest lately. Generally speaking, conventional Model-Based (MB) or Model-Free (MF) RL algorithms are not directly applicable to the MARL problems due to utilization of a fixed reward model for learning the underlying value function. While Deep Neural Network (DNN)-based solutions perform well, they are still prone to overfitting, high sensitivity to parameter selection, and sample inefficiency. In this paper, an adaptive Kalman Filter (KF)-based framework is introduced as an efficient alternative to address the aforementioned problems by capitalizing on unique characteristics of KF such as uncertainty modeling and online second order learning. More specifically, the paper proposes the Multi-Agent Adaptive Kalman Temporal Difference (MAK-TD) framework and its Successor Representation-based variant, referred to as the MAK-SR. The proposed MAK-TD/SR frameworks consider the continuous nature of the action-space that is associated with high dimensional multi-agent environments and exploit Kalman Temporal Difference (KTD) to address the parameter uncertainty. The proposed MAK-TD/SR frameworks are evaluated via several experiments, which are implemented through the OpenAI Gym MARL benchmarks. In these experiments, different number of agents in cooperative, competitive, and mixed (cooperative-competitive) scenarios are utilized. The experimental results illustrate superior performance of the proposed MAK-TD/SR frameworks compared to their state-of-the-art counterparts. [ABSTRACT FROM AUTHOR]

Wearable Biosensor Technology (WBT) has emerged as a transformative tool in the educational system over the past decade. This systematic review encompasses a comprehensive analysis of WBT utilization in educational settings over a 10-year span (2012–2022), highlighting the evolution of this field to address challenges in education by integrating technology to solve specific educational challenges, such as enhancing student engagement, monitoring stress and cognitive load, improving learning experiences, and providing real-time feedback for both students and educators. By exploring these aspects, this review sheds light on the potential implications of WBT on the future of learning. A rigorous and systematic search of major academic databases, including Google Scholar and Scopus, was conducted in accordance with the PRISMA guidelines. Relevant studies were selected based on predefined inclusion and exclusion criteria. The articles selected were assessed for methodological quality and bias using established tools. The process of data extraction and synthesis followed a structured framework. Key findings include the shift from theoretical exploration to practical implementation, with EEG being the predominant measurement, aiming to explore mental states, physiological constructs, and teaching effectiveness. Wearable biosensors are significantly impacting the educational field, serving as an important resource for educators and a tool for students. Their application has the potential to transform and optimize academic practices through sensors that capture biometric data, enabling the implementation of metrics and models to understand the development and performance of students and professors in an academic environment, as well as to gain insights into the learning process. [ABSTRACT FROM AUTHOR]

Accurate classification of human aquatic activities using radar has a variety of potential applications such as rescue operations and border patrols. Nevertheless, the classification of activities on water using radar has not been extensively studied, unlike the case on dry ground, due to its unique challenge. Namely, not only is the radar cross section of a human on water small, but the micro-Doppler signatures are much noisier due to water drops and waves. In this paper, we first investigate whether discriminative signatures could be obtained for activities on water through a simulation study. Then, we show how we can effectively achieve high classification accuracy by applying deep convolutional neural networks (DCNN) directly to the spectrogram of real measurement data. From the five-fold cross-validation on our dataset, which consists of five aquatic activities, we report that the conventional feature-based scheme only achieves an accuracy of 45.1%. In contrast, the DCNN trained using only the collected data attains 66.7%, and the transfer learned DCNN, which takes a DCNN pre-trained on a RGB image dataset and fine-tunes the parameters using the collected data, achieves a much higher 80.3%, which is a significant performance boost. [ABSTRACT FROM AUTHOR]

Mechatronics and robotics appeared particularly effective in students' education, allowing them to create non-traditional solutions in STEM disciplines, which have a direct impact and interaction with the world surrounding them. This paper presents the current state of the MiniCERNBot Educational Robotic platform for high-school and university students. The robot provides a comprehensive educative system with tutorials and tasks tuned for different ages on 3D design, mechanical assembly, control, programming, planning, and operation. The system is inspired to existing robotic systems and typical robotic interventions performed at CERN, and includes an education mock-up that follows the example of a previous real operation performed in CERN's Antimatter Factory. The paper describes the learning paths where the MiniCERNBot platform can be used by students, at different ages and disciplines. In addition, it describes the software and hardware architecture, presenting results on modularity and network performance during education exercises. In summary, the objective of the study is improving the way STEM educational and dissemination activities at CERN Robotics Lab are performed, as well as their possible synergies with other education institutions, such as High-Schools and Universities, improving the learning collaborative process and inspiring students interested in technical studies. To this end, a new educational robotic platform has been designed, inspired on real scientific operations, which allows the students practice multidisciplinary STEM skills in a collaborative problem-solving way, while increasing their motivation and comprehension of the research activities. [ABSTRACT FROM AUTHOR]

Learning underlying patterns from sensory data is crucial in the Human Activity Recognition (HAR) task to avoid poor generalization when coping with unseen data. A key solution to such an issue is representation learning, which becomes essential when input signals contain activities with similar patterns or when patterns generated by different subjects for the same activity vary. To address these issues, we seek a solution to increase generalization by learning the underlying factors of each sensor signal. We develop a novel multi-channel asymmetric auto-encoder to recreate input signals precisely and extract indicative unsupervised futures. Further, we investigate the role of various activation functions in signal reconstruction to ensure the model preserves the patterns of each activity in the output. Our main contribution is that we propose a multi-task learning model to enhance representation learning through shared layers between signal reconstruction and the HAR task to improve the robustness of the model in coping with users not included in the training phase. The proposed model learns shared features between different tasks that are indeed the underlying factors of each input signal. We validate our multi-task learning model using several publicly available HAR datasets, UCI-HAR, MHealth, PAMAP2, and USC-HAD, and an in-house alpine skiing dataset collected in the wild, where our model achieved 99%, 99%, 95%, 88%, and 92% accuracy. Our proposed method shows consistent performance and good generalization on all the datasets compared to the state of the art. [ABSTRACT FROM AUTHOR]

Robot grasping constitutes an essential capability in fulfilling the complexities of advanced industrial operations. This field has been extensively investigated to address a range of practical applications. However, the generation of a stable grasp remains challenging, principally due to the constraints imposed by object geometries and the diverse objectives of the tasks. In this work, we propose a novel learning from demonstration-based grasp-planning framework. This framework is designed to extract crucial human grasp skills, namely the contact region and approach direction, from a single demonstration. Then, it formulates an optimization problem that integrates the extracted skills to generate a stable grasp. Distinct from conventional methods that rely on learning implicit synergies through human demonstration or on mapping the dissimilar kinematics between human hands and robot grippers, our approach focuses on learning the intuitive human intent that involves the potential contact regions and the grasping approach direction. Furthermore, our optimization formulation is capable of identifying the optimal grasp by minimizing the surface fitting error between the demonstrated contact regions on the object and the gripper finger surface and imposing a penalty for any misalignment between the demonstrated and the gripper's approach directions. A series of experiments is conducted to verify the effectiveness of the proposed algorithm through both simulations and real-world scenarios. [ABSTRACT FROM AUTHOR]

In modern logistics, the box-in-box insertion task is representative of a wide range of packaging applications, and automating compliant object insertion is difficult due to challenges in modelling the object deformation during insertion. Using Learning from Demonstration (LfD) paradigms, which are frequently used in robotics to facilitate skill transfer from humans to robots, can be one solution for complex tasks that are difficult to mathematically model. In order to automate the box-in-box insertion task for packaging applications, this study makes use of LfD techniques. The proposed framework has three phases. Firstly, a master–slave teleoperated robot system is used in the initial phase to haptically demonstrate the insertion task. Then, the learning phase involves identifying trends in the demonstrated trajectories using probabilistic methods, in this case, Gaussian Mixture Regression. In the third phase, the insertion task is generalised, and the robot adjusts to any object position using barycentric interpolation. This method is novel because it tackles tight insertion by taking advantage of the boxes' natural compliance, making it possible to complete the task even with a position-controlled robot. To determine whether the strategy is generalisable and repeatable, experimental validation was carried out. [ABSTRACT FROM AUTHOR]

When assessing trainees' progresses during a driving training program, instructors can only rely on the evaluation of a trainee's explicit behavior and their performance, without having any insight about the training effects at a cognitive level. However, being able to drive does not imply knowing how to drive safely in a complex scenario such as the road traffic. Indeed, the latter point involves mental aspects, such as the ability to manage and allocate one's mental effort appropriately, which are difficult to assess objectively. In this scenario, this study investigates the validity of deploying an electroencephalographic neurometric of mental effort, obtained through a wearable electroencephalographic device, to improve the assessment of the trainee. The study engaged 22 young people, without or with limited driving experience. They were asked to drive along five different but similar urban routes, while their brain activity was recorded through electroencephalography. Moreover, driving performance, subjective and reaction times measures were collected for a multimodal analysis. In terms of subjective and performance measures, no driving improvement could be detected either through the driver's subjective measures or through their driving performance. On the other side, through the electroencephalographic neurometric of mental effort, it was possible to catch their improvement in terms of mental performance, with a decrease in experienced mental demand after three repetitions of the driving training tasks. These results were confirmed by the analysis of reaction times, that significantly improved from the third repetition as well. Therefore, being able to measure when a task is less mentally demanding, and so more automatic, allows to deduce the degree of users training, becoming capable of handling additional tasks and reacting to unexpected events. [ABSTRACT FROM AUTHOR]

With the increasing demand for person re-identification (Re-ID) tasks, the need for all-day retrieval has become an inevitable trend. Nevertheless, single-modal Re-ID is no longer sufficient to meet this requirement, making Multi-Modal Data crucial in Re-ID. Consequently, a Visible-Infrared Person Re-Identification (VI Re-ID) task is proposed, which aims to match pairs of person images from the visible and infrared modalities. The significant modality discrepancy between the modalities poses a major challenge. Existing VI Re-ID methods focus on cross-modal feature learning and modal transformation to alleviate the discrepancy but overlook the impact of person contour information. Contours exhibit modality invariance, which is vital for learning effective identity representations and cross-modal matching. In addition, due to the low intra-modal diversity in the visible modality, it is difficult to distinguish the boundaries between some hard samples. To address these issues, we propose the Graph Sampling-based Multi-stream Enhancement Network (GSMEN). Firstly, the Contour Expansion Module (CEM) incorporates the contour information of a person into the original samples, further reducing the modality discrepancy and leading to improved matching stability between image pairs of different modalities. Additionally, to better distinguish cross-modal hard sample pairs during the training process, an innovative Cross-modality Graph Sampler (CGS) is designed for sample selection before training. The CGS calculates the feature distance between samples from different modalities and groups similar samples into the same batch during the training process, effectively exploring the boundary relationships between hard classes in the cross-modal setting. Some experiments conducted on the SYSU-MM01 and RegDB datasets demonstrate the superiority of our proposed method. Specifically, in the VIS→IR task, the experimental results on the RegDB dataset achieve 93.69% for Rank-1 and 92.56% for mAP. [ABSTRACT FROM AUTHOR]

In classification tasks, such as face recognition and emotion recognition, multimodal information is used for accurate classification. Once a multimodal classification model is trained with a set of modalities, it estimates the class label by using the entire modality set. A trained classifier is typically not formulated to perform classification for various subsets of modalities. Thus, the model would be useful and portable if it could be used for any subset of modalities. We refer to this problem as the multimodal portability problem. Moreover, in the multimodal model, classification accuracy is reduced when one or more modalities are missing. We term this problem the missing modality problem. This article proposes a novel deep learning model, termed KModNet, and a novel learning strategy, termed progressive learning, to simultaneously address missing modality and multimodal portability problems. KModNet, formulated with the transformer, contains multiple branches corresponding to different k-combinations of the modality set S. KModNet is trained using a multi-step progressive learning framework, where the k-th step uses a k-modal model to train different branches up to the k-th combination branch. To address the missing modality problem, the training multimodal data is randomly ablated. The proposed learning framework is formulated and validated using two multimodal classification problems: audio-video-thermal person classification and audio-video emotion classification. The two classification problems are validated using the Speaking Faces, RAVDESS, and SAVEE datasets. The results demonstrate that the progressive learning framework enhances the robustness of multimodal classification, even under the conditions of missing modalities, while being portable to different modality subsets. [ABSTRACT FROM AUTHOR]

Self-supervised learning models, such as BERT, have improved the performance of various tasks in natural language processing. Although the effect is reduced in the out-of-domain field and not the the trained domain thus representing a limitation, it is difficult to train a new language model for a specific domain since it is both time-consuming and requires large amounts of data. We propose a method to quickly and effectively apply the pre-trained language models trained in the general domain to a specific domain's vocabulary without re-training. An extended vocabulary list is obtained by extracting a meaningful wordpiece from the training data of the downstream task. We introduce curriculum learning, training the models with two successive updates, to adapt the embedding value of the new vocabulary. It is convenient to apply because all training of the models for downstream tasks are performed in one run. To confirm the effectiveness of the proposed method, we conducted experiments on AIDA-SC, AIDA-FC, and KLUE-TC, which are Korean classification tasks, and subsequently achieved stable performance improvement. [ABSTRACT FROM AUTHOR]

Locomotor impairment is a highly prevalent and significant source of disability and significantly impacts the quality of life of a large portion of the population. Despite decades of research on human locomotion, challenges remain in simulating human movement to study the features of musculoskeletal drivers and clinical conditions. Most recent efforts to utilize reinforcement learning (RL) techniques are promising in the simulation of human locomotion and reveal musculoskeletal drives. However, these simulations often fail to mimic natural human locomotion because most reinforcement strategies have yet to consider any reference data regarding human movement. To address these challenges, in this study, we designed a reward function based on the trajectory optimization rewards (TOR) and bio-inspired rewards, which includes the rewards obtained from reference motion data captured by a single Inertial Moment Unit (IMU) sensor. The sensor was equipped on the participants' pelvis to capture reference motion data. We also adapted the reward function by leveraging previous research on walking simulations for TOR. The experimental results showed that the simulated agents with the modified reward function performed better in mimicking the collected IMU data from participants, which means that the simulated human locomotion was more realistic. As a bio-inspired defined cost, IMU data enhanced the agent's capacity to converge during the training process. As a result, the models' convergence was faster than those developed without reference motion data. Consequently, human locomotion can be simulated more quickly and in a broader range of environments, with a better simulation performance. [ABSTRACT FROM AUTHOR]

Nowadays, the solution to many practical problems relies on machine learning tools. However, compiling the appropriate training data set for real-world classification problems is challenging because collecting the right amount of data for each class is often difficult or even impossible. In such cases, we can easily face the problem of imbalanced learning. There are many methods in the literature for solving the imbalanced learning problem, so it has become a serious question how to compare the performance of the imbalanced learning methods. Inadequate validation techniques can provide misleading results (e.g., due to data shift), which leads to the development of methods designed for imbalanced data sets, such as stratified cross-validation (SCV) and distribution optimally balanced SCV (DOB-SCV). Previous studies have shown that higher classification performance scores (AUC) can be achieved on imbalanced data sets using DOB-SCV instead of SCV. We investigated the effect of the oversamplers on this difference. The study was conducted on 420 data sets, involving several sampling methods and the DTree, kNN, SVM, and MLP classifiers. We point out that DOB-SCV often provides a little higher F1 and AUC values for classification combined with sampling. However, the results also prove that the selection of the sampler–classifier pair is more important for the classification performance than the choice between the DOB-SCV and the SCV techniques. [ABSTRACT FROM AUTHOR]

Mei et al. [[13]] studied the two-dimensional direction of arrival (2D-DOA) estimation problem in a switching uniform circular array (SUCA), and proposed a covariance matrix completion algorithm for 2D-DOA estimation in a SUCA. The Special Issue "Signal Processing and Machine Learning for Smart Sensing Applications" focused on the publication of advanced signal processing methods by means of state-of-the-art machine learning technologies for smart sensing applications. Monte-Carlo simulations are performed to evaluate the GSCA algorithm, the spatial spectrum plots and RMSE curves demonstrated that the GSCA algorithm can give reasonable results of underdetermined DOA estimation in SCA. The defect detection algorithm based on YOLO algorithms made it possible to obtain results more quickly and with higher mean average precision (mAP) than that of existing methods. [Extracted from the article]

Due to the distributed data collection and learning in federated learnings, many clients conduct local training with non-independent and identically distributed (non-IID) datasets. Accordingly, the training from these datasets results in severe performance degradation. We propose an efficient algorithm for enhancing the performance of federated learning by overcoming the negative effects of non-IID datasets. First, the intra-client class imbalance is reduced by rendering the class distribution of clients close to Uniform distribution. Second, the clients to participate in federated learning are selected to make their integrated class distribution close to Uniform distribution for the purpose of mitigating the inter-client class imbalance, which represents the class distribution difference among clients. In addition, the amount of local training data for the selected clients is finely adjusted. Finally, in order to increase the efficiency of federated learning, the batch size and the learning rate of local training for the selected clients are dynamically controlled reflecting the effective size of the local dataset for each client. In the performance evaluation on CIFAR-10 and MNIST datasets, the proposed algorithm achieves 20% higher accuracy than existing federated learning algorithms. Moreover, in achieving this huge accuracy improvement, the proposed algorithm uses less computation and communication resources compared to existing algorithms in terms of the amount of data used and the number of clients joined in the training. [ABSTRACT FROM AUTHOR]

Force myography (FMG) signals can read volumetric changes of muscle movements, while a human participant interacts with the environment. For collaborative activities, FMG signals could potentially provide a viable solution to controlling manipulators. In this paper, a novel method to interact with a two-degree-of-freedom (DoF) system consisting of two perpendicular linear stages using FMG is investigated. The method consists in estimating exerted hand forces in dynamic arm motions of a participant using FMG signals to provide velocity commands to the biaxial stage during interactions. Five different arm motion patterns with increasing complexities, i.e., "x-direction", "y-direction", "diagonal", "square", and "diamond", were considered as human intentions to manipulate the stage within its planar workspace. FMG-based force estimation was implemented and evaluated with a support vector regressor (SVR) and a kernel ridge regressor (KRR). Real-time assessments, where 10 healthy participants were asked to interact with the biaxial stage by exerted hand forces in the five intended arm motions mentioned above, were conducted. Both the SVR and the KRR obtained higher estimation accuracies of 90–94% during interactions with simple arm motions (x-direction and y-direction), while for complex arm motions (diagonal, square, and diamond) the notable accuracies of 82–89% supported the viability of the FMG-based interactive control. [ABSTRACT FROM AUTHOR]

Autonomous motion planning (AMP) of unmanned aerial vehicles (UAVs) is aimed at enabling a UAV to safely fly to the target without human intervention. Recently, several emerging deep reinforcement learning (DRL) methods have been employed to address the AMP problem in some simplified environments, and these methods have yielded good results. This paper proposes a multiple experience pools (MEPs) framework leveraging human expert experiences for DRL to speed up the learning process. Based on the deep deterministic policy gradient (DDPG) algorithm, a MEP–DDPG algorithm was designed using model predictive control and simulated annealing to generate expert experiences. On applying this algorithm to a complex unknown simulation environment constructed based on the parameters of the real UAV, the training experiment results showed that the novel DRL algorithm resulted in a performance improvement exceeding 20% as compared with the state-of-the-art DDPG. The results of the experimental testing indicate that UAVs trained using MEP–DDPG can stably complete a variety of tasks in complex, unknown environments. [ABSTRACT FROM AUTHOR]

Herein, we propose an unsupervised learning architecture under coupled consistency conditions to estimate the depth, ego-motion, and optical flow. Previously invented learning techniques in computer vision adopted a large amount of the ground truth dataset for network training. A ground truth dataset, including depth and optical flow collected from the real world, requires tremendous effort in pre-processing due to the exposure to noise artifacts. In this paper, we propose a framework that trains networks while using a different type of data with combined losses that are derived from a coupled consistency structure. The core concept is composed of two parts. First, we compare the optical flows, which are estimated from both the depth plus ego-motion and flow estimation network. Subsequently, to prevent the effects of the artifacts of the occluded regions in the estimated optical flow, we compute flow local consistency along the forward–backward directions. Second, synthesis consistency enables the exploration of the geometric correlation between the spatial and temporal domains in a stereo video. We perform extensive experiments on the depth, ego-motion, and optical flow estimation on the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset. We verify that the flow local consistency loss improves the optical flow accuracy in terms of the occluded regions. Furthermore, we also show that the view-synthesis-based photometric loss enhances the depth and ego-motion accuracy via scene projection. The experimental results exhibit the competitive performance of the estimated depth and the optical flow; moreover, the induced ego-motion is comparable to that obtained from other unsupervised methods. [ABSTRACT FROM AUTHOR]

The availability of educational data obtained by technology-assisted learning platforms can potentially be used to mine student behavior in order to address their problems and enhance the learning process. Educational data mining provides insights for professionals to make appropriate decisions. Learning platforms complement traditional learning environments and provide an opportunity to analyze students' performance, thus mitigating the probability of student failures. Predicting students' academic performance has become an important research area to take timely corrective actions, thereby increasing the efficacy of education systems. This study proposes an improved conditional generative adversarial network (CGAN) in combination with a deep-layer-based support vector machine (SVM) to predict students' performance through school and home tutoring. Students' educational datasets are predominantly small in size; to handle this problem, synthetic data samples are generated by an improved CGAN. To prove its effectiveness, results are compared with and without applying CGAN. Results indicate that school and home tutoring combined have a positive impact on students' performance when the model is trained after applying CGAN. For an extensive evaluation of deep SVM, multiple kernel-based approaches are investigated, including radial, linear, sigmoid, and polynomial functions, and their performance is analyzed. The proposed improved CGAN coupled with deep SVM outperforms in terms of sensitivity, specificity, and area under the curve when compared with solutions from the existing literature. [ABSTRACT FROM AUTHOR]

Interest in autonomous vehicles (AVs) has significantly increased in recent years, but despite the huge research efforts carried out in the field of intelligent transportation systems (ITSs), several technological challenges must still be addressed before AVs can be extensively deployed in any environment. In this context, one of the key technological enablers is represented by the motion-planning and control system, with the aim of guaranteeing the occupants comfort and safety. In this paper, a trajectory-planning and control algorithm is developed based on a Model Predictive Control (MPC) approach that is able to work in different road scenarios (such as urban areas and motorways). This MPC is designed considering imitation-learning from a specific dataset (from real-world overtaking maneuver data), with the aim of getting human-like behavior. The algorithm is used to generate optimal trajectories and control the vehicle dynamics. Simulations and Hardware-In-the-Loop tests are carried out to demonstrate the effectiveness and computation efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

There is a strong increase in the use of devices that measure physiological arousal through electrodermal activity (EDA). Although there is a long tradition of studying emotions during learning, researchers have only recently started to use EDA to measure emotions in the context of education and learning. This systematic review aimed to provide insight into how EDA is currently used in these settings. The review aimed to investigate the methodological aspects of EDA measures in educational research and synthesize existing empirical evidence on the relation of physiological arousal, as measured by EDA, with learning outcomes and learning processes. The methodological results pointed to considerable variation in the usage of EDA in educational research and indicated that few implicit standards exist. Results regarding learning revealed inconsistent associations between physiological arousal and learning outcomes, which seem mainly due to underlying methodological differences. Furthermore, EDA frequently fluctuated during different stages of the learning process. Compared to this unimodal approach, multimodal designs provide the potential to better understand these fluctuations at critical moments. Overall, this review signals a clear need for explicit guidelines and standards for EDA processing in educational research in order to build a more profound understanding of the role of physiological arousal during learning. [ABSTRACT FROM AUTHOR]

This article performs a Systematic Review of studies to answer the question: What are the researches related to the learning process with (Serious) Business Games using data collection techniques with Electroencephalogram or Eye tracking signals? The PRISMA declaration method was used to guide the search and inclusion of works related to the elaboration of this study. The 19 references resulting from the critical evaluation initially point to a gap in investigations into using these devices to monitor serious games for learning in organizational environments. An approximation with equivalent sensing studies in serious games for the contribution of skills and competencies indicates that continuous monitoring measures, such as mental state and eye fixation, proved to identify the players' attention levels effectively. Also, these studies showed effectiveness in the flow at different moments of the task, motivating and justifying the replication of these studies as a source of insights for the optimized design of business learning tools. This study is the first systematic review and consolidates the existing literature on user experience analysis of business simulation games supported by human-computer interfaces. [ABSTRACT FROM AUTHOR]

This study evaluates and compares the suitability for child–computer interaction (CCI, the branch within human–computer interaction focused on interactive computer systems for children) of two devices: a standard computer mouse and the ENLAZA interface, a head mouse that measures the user's head posture using an inertial sensor. A multidirectional pointing task was used to assess the motor performance and the users' ability to learn such a task. The evaluation was based on the interpretation of the metrics derived from Fitts' law. Ten children aged between 6 and 8 participated in this study. Participants performed a series of pre- and post-training tests for both input devices. After the experiments, data were analyzed and statistically compared. The results show that Fitts' law can be used to detect changes in the learning process and assess the level of psychomotor development (by comparing the performance of adults and children). In addition, meaningful differences between the fine motor control (hand) and the gross motor control (head) were found by comparing the results of the interaction using the two devices. These findings suggest that Fitts' law metrics offer a reliable and objective way of measuring the progress of physical training or therapy. [ABSTRACT FROM AUTHOR]