Learning Phase Research Articles

Influence of reinforcement learning on the inhibitory control of Internet gaming disorder.

Reward processing dysfunction and inhibition control deficiency have been observed in Internet gaming disorder (IGD). However, it is still unclear whether the previous reinforcement learning depends on reward/punishment feedback influences on the cognitive inhibitory control of IGD. This study compared the differences between an IGD group and healthy people without game experiences in the probability selection task and the subsequent stop signal task by the method of behavioral experiments, in order to explore whether the reward learning ability is impaired in the IGD group. We also discuss the influence of previous reward learning on subsequent inhibition control. The results showed that (1) during the reward learning phase, the IGD group's accuracy was significantly lower than that of the control group; (2) compared with the control group, the IGD group's reaction times were longer in the transfer phase; (3) for no-go trials of the inhibitory control phase after reward learning, the accuracy of the reward-related stimulation in the IGD group was lower than that of punishment-related or neutral stimulation, but there was no significant difference among the three conditions in the control group. These findings indicated that the reinforcement learning ability of the IGD group was impaired, which further caused the abnormal response to reinforcement stimuli.

Low-resource entity resolution with domain generalization and active learning

Entity Resolution (ER), a fundamental task in data cleaning and integration, is critical in various fields such as healthcare, e-commerce, and social networks. Traditional ER methods are constrained by the need for substantial labeled samples and the challenge of generalization to unseen domains. To address the low-resource challenge in ER, a novel two-phase framework is proposed. Initially, we introduce the Domain Generalization Entity Resolution (DGER) framework, combining domain adversarial learning and simulated target learning to improve the generalization performance on unseen target domains. Subsequently, to further adapt to the target dataset, we present a novel active learning approach called Domain-Aware Uncertainty Active Learning (DUAL), for fine-tuning the DGER model with minimal annotation cost. DUAL manually annotates target domain samples that are highly uncertain and exhibit high divergence from the source, while assigning pseudo-labels to high-confidence samples. Experimental results on multiple real-world datasets demonstrate that our framework outperforms traditional ER methods in generalizing to unseen domains. Specifically, our DGER method outperforms the best-performing ER baseline in each task, achieving an average F1 score improvement of 9.02% across eight different test tasks. Moreover, within a limited annotation budget during the active learning phase, our DUAL fine-tuning strategy for the ER model outperforms uncertainty-based active learning techniques.

Physics-Informed Online Learning for Temperature Prediction in Metal AM.

In metal additive manufacturing (AM), precise temperature field prediction is crucial for process monitoring, automation, control, and optimization. Traditional methods, primarily offline and data-driven, struggle with adapting to real-time changes and new process scenarios, which limits their applicability for effective AM process control. To address these challenges, this paper introduces the first physics-informed (PI) online learning framework specifically designed for temperature prediction in metal AM. Utilizing a physics-informed neural network (PINN), this framework integrates a neural network architecture with physics-informed inputs and loss functions. Pretrained on a known process to establish a baseline, the PINN transitions to an online learning phase, dynamically updating its weights in response to new, unseen data. This adaptation allows the model to continuously refine its predictions in real-time. By integrating physics-informed components, the PINN leverages prior knowledge about the manufacturing processes, enabling rapid adjustments to process parameters, geometries, deposition patterns, and materials. Empirical results confirm the robust performance of this PI online learning framework in accurately predicting temperature fields for unseen processes across various conditions. It notably surpasses traditional data-driven models, especially in critical areas like the Heat Affected Zone (HAZ) and melt pool. The PINN's use of physical laws and prior knowledge not only provides a significant advantage over conventional models but also ensures more accurate predictions under diverse conditions. Furthermore, our analysis of key hyperparameters-the learning rate and batch size of the online learning phase-highlights their roles in optimizing the learning process and enhancing the framework's overall effectiveness. This approach demonstrates significant potential to improve the online control and optimization of metal AM processes.

Broadening the scope: Multiple functional connectivity networks underlying threat conditioning and extinction

Abstract Threat learning processes are thought to be foundational to anxiety and fear-related disorders. However, the study of these processes in the human brain has largely focused on specific brain regions, owing partly to the ease of translating between these regions in human and nonhuman animals. Moving beyond analyzing focal regions of interest to whole-brain dynamics and connectivity during threat learning is essential for understanding the neuropathology of fear-related disorders in humans. In this study, 223 participants completed a 2-day Pavlovian threat conditioning paradigm while undergoing fMRI. Participants completed threat acquisition and extinction. Extinction recall was assessed 48 hours later. Using a data-driven group independent component analysis (ICA), we examined large-scale functional connectivity networks during each phase of threat learning. Connectivity networks were tested to see how they responded to conditioned stimuli during early and late phases of threat acquisition and extinction as well as during early trials of extinction recall. A network overlapping with the default mode network involving hippocampus, ventromedial prefrontal cortex (vmPFC), and posterior cingulate was implicated in threat acquisition and extinction. Another network overlapping with the salience network involving dorsal anterior cingulate cortex (dACC), mPFC, and inferior frontal gyrus was implicated both in threat acquisition and in extinction recall. Other networks overlapping with parts of the salience, somatomotor, visual, and frontoparietal networks were involved in the acquisition or in the extinction of learned threat responses. These findings help support the functional cooperation of specific brain regions during threat learning in a model-free fashion while introducing new findings of spatially independent functional connectivity networks during threat and safety learning. Rather than being a single process in a core network of regions, threat learning involves multiple brain networks operating in parallel performing different functions at different timescales. Understanding the nature and interplay of these dynamics will be critical for comprehensive understanding of the multiple processes that may be at play in the neuropathology of anxiety and fear-related disorders.

The Learning Curve for Robotic Lateral Pelvic Lymph Node Dissection for Rectal Cancer: A View from the West.

Lateral pelvic lymph-node dissection is performed for selected patients with rectal cancer with persistent lateral nodal disease after neoadjuvant therapy. This technique has been slow to be adopted in the West due to concerns regarding technical difficulty. This is the first report on the learning curve for lateral pelvic lymph node dissection in the US or Europe. The aim of this study was to analyze the learning curve associated with robotic lateral pelvic lymph node dissection. Retrospective observational cohort. Tertiary academic cancer center. Consecutive patients from 2012 to 2021. All patients underwent robotic lateral pelvic lymph node dissection. The primary endpoints were the learning curves for maximum number of nodes retrieved and urinary retention which was evaluated with simple cumulative-sum and two-sided Bernoulli cumulative-sum charts. Fifty-four procedures were included. A single-surgeon (n = 35) and an institutional learning curve are presented in the analysis. In the single-surgeon learning curve, a turning point marking the end of a learning phase was detected at the 12th procedure for the number of retrieved nodes and at the 20th for urinary retention. In the institutional learning curve analysis, two turning points were identified at the 13th and 26th procedures indicating progressive improvements for the number of retrieved nodes and at the 27th for urinary retention. No sustained alarm signals were detected at any time point. The retrospective nature, small sample size and the referral center nature of the reporting institution that may limit generalizability. In a setting of institutional experience with robotic colorectal surgery including beyond TME resections, the learning curve for robotic lateral pelvic lymph node dissection is acceptably short. Our results demonstrate feasibility of acquisition of this technique in a controlled setting, with sufficient case volume and proctoring can optimize the learning curve. See Video Abstract.

Improving Reinforcement Learning Exploration by Autoencoders

Reinforcement learning is a field with massive potential related to solving engineering problems without field knowledge. However, the problem of exploration and exploitation emerges when one tries to balance a system between the learning phase and proper execution. In this paper, a new method is proposed that utilizes autoencoders to manage the exploration rate in an epsilon-greedy exploration algorithm. The error between the real state and the reconstructed state by the autoencoder becomes the base of the exploration-exploitation rate. The proposed method is then examined in two experiments: one benchmark is the cartpole experiment while the other is a gridworld example created for this paper to examine long-term exploration. Both experiments show results such that the proposed method performs better in these scenarios.

Experimental vibration-based output-only damage localization of mechanical systems

Vibration-based Structural Health Monitoring (SHM) is becoming increasingly widespread in a variety of engineering sectors as its variability enables diverse applications. It enables full-time assessment of the status of a structure, allowing for early maintenance and repair to prevent further damage or even failure. The presented study is part of the SPP100+ program, which has the objective of extending the usability of complex structures. This study presents an experimental investigation of the damage localization of mechanical structures while considering varying environmental and operational conditions (EOC). For this, a testing field was designed and applied, enabling one to study the effects of the varying conditions in a comparable way. The research is based on the approach to modify the state projection estimation error (SP2E) method to account for the influence of EOC. The proposed method utilizes output-only system identification and state space parameterization to estimate the current structural state. Stochastic subspace identification (SSI) and H_∞ -estimation are employed to identify the state space model during a learning phase. Subsequently, the SP2E method is applied during the monitoring phase to localize structural alterations. Moreover, an algorithm is introduced to estimate the weighting factors of different environmental and operational conditions. To verify the efficacy of the proposed method, an extensive experimental study is conducted. The numerical analysis successfully demonstrates the applicability of the method for localizing mass perturbation and stiffness degradation under various EOC. This work contributes to proactive maintenance and damage detection for mechanical structures under varying conditions.

Continuous mapping of deformation over a ship structure model based on pointwise measurements

The development of structural monitoring systems on-board vehicles aims to achieve a full-picture of the vehicle response under operating conditions. The use of different data sources is a key point for many SHM approaches which demand for extensive information and data fusion techniques to address the specific inverse problem in a robust way. Therefore, a procedure to transform pointwise measurements into a continuous representation of the monitored structure is presented in this paper. To achieve the desired monitoring goals, a numerical approach which combines experimental recorded data and modelled responses from a ship structural model is developed. Craig-Bampton truncation technique is applied on the FE vehicle model to reduce elastic dofs and obtain a computationally cost-effective model. The main advantage of Craig-Bampton modes is the capability to keep unchanged the information at the sensor nodes. A state observer is then built to evaluate the elastic deflection field and the loads over the structure in the points where no measurement is available. A natural second-order observer is exploited as it is more suited for the present application than the Kalman filter. To enhance the observer performances, an optimization process is carried out based on a learning phase. Following a previous paper about theoretical aspects of the virtual sensing approach on 1D structures. the developed techniques are here applied to the monitoring of the structural deflections and the ambient excitation relative to an elastically scaled model of a fast catamaran, tested in the towing-tank. Accelerations and strain-gage data are used to reconstruct the elastic deformations of the physical model metallic backbone scaling the reference ship behavior. Hydrodynamic load data relative to the demihull portions and the wetdeck are obtained as well.

Determination of the Best Feature Subset for Learner Migration in Limpopo

The South African Education Management Information Systems (EMIS) hosts longitudinal data on school inventory, learners, and educators. One of the most prevailing and yet ignored phases in machine learning is Feature Selection (FS). Neglecting this phase can adversely impact the outcome of the machine-learning exercise. This study seeks to explore informative features from the EMIS system which can predict the possibility of learners prematurely transitioning to alternative learning spaces in the Limpopo education system. The Ravenstein migration theory was used to assemble the initial features which were then subjected to Boruta, RPART, Adaboost.M1, and J48 algorithms. The feature subsets generated by the FS algorithms were compared with filter-based statistical methods such as Spearman Correlation and Mutual Information to aid in the final selection of the best feature subset for the study. All machine learning FS methods performed well. Feature subset generated by Boruta was considered optimal due to relatively low importance score variance among the selected features compared to RPART, J48, and Adaboost.M1. It is believed that the low variance in the feature set will improve the model's stability and its ability to generalize with previously unseen data.

The challenge of learning adaptive mental behavior.

Many psychotherapies aim to help people replace maladaptive mental behaviors (such as those leading to unproductive worry) with more adaptive ones (such as those leading to active problem solving). Yet, little is known empirically about how challenging it is to learn adaptive mental behaviors. Mental behaviors entail taking mental operations and thus may be more challenging to perform than motor actions; this challenge may enhance or impair learning. In particular, challenge when learning is often desirable because it improves retention. Yet, it is also plausible that the necessity of carrying out mental operations interferes with learning the expected values of mental actions by impeding credit assignment: the process of updating an action's value after reinforcement. Then, it may be more challenging not only to perform-but also to learn the consequences of-mental (vs. motor) behaviors. We designed a task to assess learning to take adaptive mental versus motor actions via matched probabilistic feedback. In two experiments (N = 300), most participants found it more difficult to learn to select optimal mental (vs. motor) actions, as evident in worse accuracy not only in a learning but also test (retention) phase. Computational modeling traced this impairment to an indicator of worse credit assignment (impaired construction and maintenance of expected values) when learning mental actions, accounting for worse accuracy in the learning and retention phases. The results suggest that people have particular difficulty learning adaptive mental behavior and pave the way for novel interventions to scaffold credit assignment and promote adaptive thinking. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Teaching Antimicrobial Decision-Making in Medical Education: A Qualitative Study

Background: Inappropriate use of antimicrobials contributes to the growing threat of antibiotic resistance. While physicians encounter infections in virtually every facet of medical practice, research has shown that physicians have difficulty determining the need for antimicrobials and choosing the right drug. Physicians’ difficulties with antimicrobial prescribing likely begin early in medical education, yet little is known about how medical students learn to make antimicrobial choices. Our study sought to better understand how medical students learn antimicrobial decision-making, including the impact of a new learning tool introduced in the Infectious Diseases (ID) and Microbiology preclinical course. Method: From 2021-2023, we conducted 18 individual interviews with a purposive sample of medical students at the University of Michigan who had taken the preclinical ID/Microbiology course during the 2019-2021 curricular years. We asked participants how they learned to make antimicrobial decisions and how the course and clinical rotations influenced their understanding of antimicrobial choice. The six participants who took the 2021 course were additionally asked how an antimicrobial decision-making tool introduced that year impacted that process (Figure 1). The tool was adapted from prior work on antimicrobial reasoning (Abdoler et al, 2020). Participants were asked whether they remembered being introduced to the tool (approximately 18 months prior) and if they utilized it during their clinical rotations. Results were analyzed using Dedoose Software to facilitate thematic analysis. Result: Several themes emerged on analysis. Nearly all participants reflected that they learned elements of antimicrobial decision-making during clinical rotations, through observation or direct interaction with physician mentors and patients. Several participants described the preclinical period as content learning, with clinical rotations providing a space to consolidate and scaffold knowledge, as well as transfer knowledge to new situations or tasks. Of the 6 students interviewed regarding the antimicrobial decision-making tool, only one remembered it and could accurately describe its components prior to being shown the tool during the interview. Conclusion: Results suggest that participants view the preclinical ID/Microbiology course primarily as an opportunity to learn content, and perceive learning antimicrobial decision-making directly from practicing physicians in the clinical portion of medical school. An antimicrobial decision-making tool introduced during the preclinical ID/Microbiology course in 2021 did not impact students’ conceptualization of how they learned this skill. Given that practicing physicians often make antimicrobial prescribing errors, regular re-introduction of the tool during clinical rotations may help bridge preclinical antimicrobial educational content to the clinical phase of learning, counteract inappropriate antimicrobial lessons encountered clinically, and ground students' burgeoning antimicrobial prescribing skills in a logical reasoning model.

Flexible multitask computation in recurrent networks utilizes shared dynamical motifs

Flexible computation is a hallmark of intelligent behavior. However, little is known about how neural networks contextually reconfigure for different computations. In the present work, we identified an algorithmic neural substrate for modular computation through the study of multitasking artificial recurrent neural networks. Dynamical systems analyses revealed learned computational strategies mirroring the modular subtask structure of the training task set. Dynamical motifs, which are recurring patterns of neural activity that implement specific computations through dynamics, such as attractors, decision boundaries and rotations, were reused across tasks. For example, tasks requiring memory of a continuous circular variable repurposed the same ring attractor. We showed that dynamical motifs were implemented by clusters of units when the unit activation function was restricted to be positive. Cluster lesions caused modular performance deficits. Motifs were reconfigured for fast transfer learning after an initial phase of learning. This work establishes dynamical motifs as a fundamental unit of compositional computation, intermediate between neuron and network. As whole-brain studies simultaneously record activity from multiple specialized systems, the dynamical motif framework will guide questions about specialization and generalization.

Using hands-on learning video assignments in online and in-person contexts: A longitudinal study

This study investigated the use of hands-on learning video assignments (HLVAs) among middle school students in China during and after the COVID-19 pandemic. Based on the results of HLVAs approach with seventh grade students at Jiefang Road School during the online learning phase, one class was selected to participate in an offline empirical, longitudinal study to further explore the impact of HLVAs approach on students’ biology learning. Two data collection instruments were used: hands-on learning students’ work evaluation instrument and model competence development instrument to detect changes in students’ modeling development. Questionnaire responses from the students in the experimental class two years later, when they were in high school, offer additional perspectives on this approach. Findings indicated that HLVAs approach improves students’ work quality, modeling skills, and biology learning outcomes. This study describes hands-on learning strategy based on embodied cognition theoretical perspectives, with implications for curriculum, instruction, and learning.

DRL approach for online user-centric QoS-Aware SFC embedding with dynamic VNF placement

In this paper, we tackle online Service Function Chaining (SFC) embedding issue in Software Defined Network (SDN)/Network Function Virtualization (NFV) enabled networks using Deep Reinforcement Learning (DRL) approach. This approach investigates the problem of Quality of Experience (QoE)/Quality of Service (QoS) driven SFC embedding with dynamic Virtual Network Functions (VNF) placement. We particularly focus on video streaming traffic requiring a given Mean Opinion Score (MOS) quantified in terms of QoE. In this regard, we propose a DRL algorithm based on Deep-Q-Network (DQN) (named DQN_QoE/QoS_SFC algorithm) implementing an optimization problem maximizing QoE while meeting QoS requirements. Our algorithm named DQN_QoE/QoS_SFC improves previous work given in Chen et al. (2018) dealing with the same issue through bringing performance evaluation of the training phase by testing the learning quality. This is achieved through using a QoE Threshold Score (QoETh−Sc) to be attained on average by the DQN_QoE/QoS_SFC agent along the last 100 runs of the training phase while maximizing the expected cumulative reward. We conduct simulation experiments through two performance metrics related to the SFC request namely QoE (QoE) and Rejection Ratio (RR). We investigate also how these metrics evolve for the proposed algorithm when compared with two standard baseline algorithms (Violent search, Random search) during learning phase to achieve satisfactory training quality. We highlight how DQN_QoE/QoS_SFC algorithm behaves along the training process and how it attempts reaching a near-optimal solution as closer as possible to the optimal solution provided by Violent search algorithm.

The impact of the left inferior frontal gyrus on fear extinction: A transcranial direct current stimulation study

IntroductionFear extinction is a fundamental component of exposure-based therapies for anxiety-related disorders. The renewal of fear in a different context after extinction highlights the importance of contextual factors. In this study, we aimed to investigate the causal role of the left inferior frontal gyrus (LiFG) in the context-dependency of fear extinction learning via administration of transcranial direct current stimulation (tDCS) over this area. Methods180 healthy subjects were assigned to 9 groups: 3 tDCS conditions (anodal, cathodal, and sham) × 3 context combinations (AAA, ABA, and ABB). The fear conditioning/extinction task was conducted over three consecutive days: acquisition, extinction learning, and extinction recall. tDCS (2 mA, 10min) was administered during the extinction learning phase over the LiFG via a 4-electrode montage. Skin conductance response (SCR) data and self-report assessments were collected. ResultsDuring the extinction learning phase, groups with excitability-enhancing anodal tDCS showed a significantly higher fear response to the threat cues compared to cathodal and sham stimulation conditions, irrespective of contextual factors. This effect was stable until the extinction recall phase. Additionally, excitability-reducing cathodal tDCS caused a significant decrease of the response difference between the threat and safety cues during the extinction recall phase. The self-report assessments showed no significant differences between the conditions throughout the experiment. ConclusionIndependent of the context, excitability enhancement of the LiFG did impair fear extinction, and led to preservation of fear memory. In contrast, excitability reduction of this area enhanced fear extinction retention. These findings imply that the LiFG plays a role in the fear extinction network, which seems to be however context-independent.

Towards a Standardization of Learning Curve Assessment in Minimally Invasive Liver Surgery.

The aim was to analyze the learning curves of minimal invasive liver surgery(MILS) and propose a standardized reporting. MILS offers benefits compared to open resections. For a safe introduction along the learning curve, formal training is recommended. However, definitions of learning curves and methods to assess it lack standardization. A systematic review of PubMed, Web of Science, and CENTRAL databases identified studies on learning curves in MILS. The primary outcome was the number needed to overcome the learning curve. Secondary outcomes included endpoints defining learning curves, and characterization of different learning phases(competency, proficiency and mastery). 60 articles with 12'241 patients and 102 learning curve analyses were included. The laparoscopic and robotic approach was evaluated in 71 and 18 analyses and both approaches combined in 13 analyses. Sixty-one analyses (60%) based the learning curve on statistical calculations. The most often used parameters to define learning curves were operative time (n=64), blood loss (n=54), conversion (n=42) and postoperative complications (n=38). Overall competency, proficiency and mastery were reached after 34 (IQR 19-56), 50 (IQR 24-74), 58 (IQR 24-100) procedures respectively. Intraoperative parameters improved earlier (operative time: competency to proficiency to mastery: -13%, 2%; blood loss: competency to proficiency to mastery: -33%, 0%; conversion rate (competency to proficiency to mastery; -21%, -29%), whereas postoperative complications improved later (competency to proficiency to mastery: -25%, -41%). This review summarizes the highest evidence on learning curves in MILS taking into account different definitions and confounding factors. A standardized three-phase reporting of learning phases (competency, proficiency, mastery) is proposed and should be followed.

Reconfigurations of cortical manifold structure during reward-based motor learning

Adaptive motor behavior depends on the coordinated activity of multiple neural systems distributed across the brain. While the role of sensorimotor cortex in motor learning has been well established, how higher-order brain systems interact with sensorimotor cortex to guide learning is less well understood. Using functional MRI, we examined human brain activity during a reward-based motor task where subjects learned to shape their hand trajectories through reinforcement feedback. We projected patterns of cortical and striatal functional connectivity onto a low-dimensional manifold space and examined how regions expanded and contracted along the manifold during learning. During early learning, we found that several sensorimotor areas in the dorsal attention network exhibited increased covariance with areas of the salience/ventral attention network and reduced covariance with areas of the default mode network (DMN). During late learning, these effects reversed, with sensorimotor areas now exhibiting increased covariance with DMN areas. However, areas in posteromedial cortex showed the opposite pattern across learning phases, with its connectivity suggesting a role in coordinating activity across different networks over time. Our results establish the neural changes that support reward-based motor learning and identify distinct transitions in the functional coupling of sensorimotor to transmodal cortex when adapting behavior.

Reconfigurations of cortical manifold structure during reward-based motor learning

Adaptive motor behavior depends on the coordinated activity of multiple neural systems distributed across the brain. While the role of sensorimotor cortex in motor learning has been well established, how higher-order brain systems interact with sensorimotor cortex to guide learning is less well understood. Using functional MRI, we examined human brain activity during a reward-based motor task where subjects learned to shape their hand trajectories through reinforcement feedback. We projected patterns of cortical and striatal functional connectivity onto a low-dimensional manifold space and examined how regions expanded and contracted along the manifold during learning. During early learning, we found that several sensorimotor areas in the dorsal attention network exhibited increased covariance with areas of the salience/ventral attention network and reduced covariance with areas of the default mode network (DMN). During late learning, these effects reversed, with sensorimotor areas now exhibiting increased covariance with DMN areas. However, areas in posteromedial cortex showed the opposite pattern across learning phases, with its connectivity suggesting a role in coordinating activity across different networks over time. Our results establish the neural changes that support reward-based motor learning and identify distinct transitions in the functional coupling of sensorimotor to transmodal cortex when adapting behavior.

Intuitionistic Fuzzy Gram-Schmidt Orthogonalized Artificial Neural Network for Solving MAGDM Problems

Objectives: To propose a suitable decision-making model based on Intuitionistic Fuzzy sets (IFSs) and Gram-Schmidt orthogonalization process for Artificial Neural Network (ANN). Methods: The IFS data sets appearing in the form of matrices are aggregated using the available aggregation operators in the literature and then the collective aggregated information is processed through Gram-Schmidt orthogonalization for the revised input vectors which is then fed into the ANN algorithm following Delta Learning Rule for the next phase. The weight updation is performed through the ANN and the output is improvised. Findings: The proposed Gram-Scmidt Orthogonalization process is utilized in Intuitionistic Fuzzy Artificial Neural Network model. The Delta learning rule is utilized in the process of the Neural Network, where the Intuitionistic Fuzzy nature of the input data is transformed into a fuzzy data and then the ranking of the alternatives is done based on the weights updation through the learning phase of the ANN. Once the vector is trained out of the learning phase, it is then processed through the activation function for the final selection of the best alternative required of the Multiple Attribute Group Decision Making (MAGDM) problem posed in this work. To demonstrate the usefulness and applicability of this new method with the Gram-Schmidt process, the numerical example also adds more insight to the proposed methodology of ANN with the application of some Linear Space techniques. Novelty: Most of the research done on Intuitionistic Fuzzy Artificial Neural Network model are based on learning rules or using some other calculations. The proposed Gram-Schmidt Orthogonalization process is used to find the orthogonal basis that are used as input training vectors in the Delta learning rule for ANN. Keywords: MAGDM, ANN, Aggregation operators, Learning Rules, Intuitionistic Fuzzy sets, Gram-Scmidt Orthogonalization

Exploring gender dynamics in cybersecurity education: A self-determination theory and social cognitive theory perspective

The cybersecurity industry is facing two major challenges as cyber threats get more serious: a shortage of skilled workers to defend against these attacks and a noticeable underrepresentation of women in the field, underscoring the critical need for diversity and skill development. This research explores variations in cybersecurity learning based on gender using the frameworks of self-determination and social cognitive theories. Conducted over two years, the research utilized a Capture The Flag (CTF) platform to facilitate learning and assess outcomes. This study explores the gender disparities in key areas such as intrinsic and extrinsic motivation, self-efficacy, conceptual grasp, and performance across five distinct cybersecurity subdomains: web exploitation, cryptography, cyber forensics, binary exploitation, and reverse engineering. The comprehensive evaluation included participant interaction with learning materials, their adeptness in practical exercises, and their achievements in a comprehensive contest covering five essential cross-domain cybersecurity concepts. Pre- and post-study surveys were instrumental in tracking shifts in motivation and self-efficacy levels. Findings pointed to notable gender-based differences in motivational aspects and self-belief following the learning phase, with conceptual understanding and the ability to replicate challenges also varying significantly between genders, highlighting disparities in educational outcomes. Domain-based analysis reveals notable gender differences: male participants excelled in solving reverse engineering and cryptography problems, whereas female participants performed better in cyber forensics and web exploitation challenges. These findings underscore the importance of tailored educational strategies in cybersecurity training to bridge the gender gap and foster a more diverse and capable workforce, addressing both the skill shortage and the need for broader representation in the field.