Related Learning Methods Research Articles

Deep Packet Inspection Model Based on Support Vector Machine for Anomaly Detection in Local Area Networks

Deep packet inspection is a network security solution that identifies and flags anomalous network traffic patterns in a local network environment. Traditional signature-based techniques for intrusion detection are limited in identifying different attacks or completely new kinds, which makes them unsuitable in some situations. In addition, most previous methods for anomaly detection have low detection rate and high false alarm. In this study, a deep packet inspection model based on support vector machine (SVM) for anomaly detection in local area networks was proposed. The proposed method combined the SelectKBest method and SVM for the categorization of anomaly in a local network environment. Results showed that the proposed method outperformed other related machine learning methods with accuracy, precision, recall, and F1-score of 94.81%, 94.03%, 94.13%, and 94.0799%, respectively. The accuracy result shows that most network traffic can be correctly identified by the SVM using the SelectKBest approach, with minimal false positives or negatives.

Implementation of Discovery Learning Model to Increase Student Interest and Learning Outcomes

This research aims to increase student interest and improve learning outcomes using the discovery learning model. This research uses the Action Research method. This research method starts with the planning, action implementation, observation, and reflection stages. Data Collection Techniques and Tools This research uses tests and observations. This class action was carried out at SMAN 1 Sungai Menang to determine students' interests and learning outcomes regarding applying the discovery learning model. This research shows an increase in interest, namely from 70.36% to 84% and student learning outcomes from the first and second cycles, namely from 25.92% to 85.17%. This increase is visible after implementing the discovery learning model, which can improve students' interests and learning outcomes. This research is implemented in two cycles; in the first cycle stage, the teacher provides a stimulus for students to identify and respond to problems and encourages students' critical thinking. In the second cycle, the teacher raises enthusiasm for learning by increasing students' interest in searching for related information and changing learning methods to make them more fun and interactive, such as through discussion activities that increase students' self-confidence and knowledge.

Automated stance detection in complex topics and small languages: The challenging case of immigration in polarizing news media.

Automated stance detection and related machine learning methods can provide useful insights for media monitoring and academic research. Many of these approaches require annotated training datasets, which limits their applicability for languages where these may not be readily available. This paper explores the applicability of large language models for automated stance detection in a challenging scenario, involving a morphologically complex, lower-resource language, and a socio-culturally complex topic, immigration. If the approach works in this case, it can be expected to perform as well or better in less demanding scenarios. We annotate a large set of pro- and anti-immigration examples to train and compare the performance of multiple language models. We also probe the usability of GPT-3.5 (that powers ChatGPT) as an instructable zero-shot classifier for the same task. The supervised models achieve acceptable performance, but GPT-3.5 yields similar accuracy. As the latter does not require tuning with annotated data, it constitutes a potentially simpler and cheaper alternative for text classification tasks, including in lower-resource languages. We further use the best-performing supervised model to investigate diachronic trends over seven years in two corpora of Estonian mainstream and right-wing populist news sources, demonstrating the applicability of automated stance detection for news analytics and media monitoring settings even in lower-resource scenarios, and discuss correspondences between stance changes and real-world events.

Formic Acid-Ammonia Heterodimer: A New Δ-Machine Learning CCSD(T)-Level Potential Energy Surface Allows Investigation of the Double Proton Transfer.

The formic acid-ammonia dimer is an important example of a hydrogen-bonded complex in which a double proton transfer can occur. Its microwave spectrum has recently been reported and rotational constants and quadrupole coupling constants were determined. Calculated estimates of the double-well barrier and the internal barriers to rotation were also reported. Here, we report a full-dimensional potential energy surface (PES) for this complex, using two closely related Δ-machine learning methods to bring it to the CCSD(T) level of accuracy. The PES dissociates smoothly and accurately. Using a 2d quantum model the ground vibrational-state tunneling splitting is estimated to be less than 10-4 cm-1. The dipole moment along the intrinsic reaction coordinate is calculated along with a Mullikan charge analysis and supports the mildly ionic character of the minimum and strongly ionic character at the double-well barrier.

Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification

AbstractWe propose a novel deep learning framework, named SYMHnet, which employs a graph neural network and a bidirectional long short‐term memory network to cooperatively learn patterns from solar wind and interplanetary magnetic field parameters for short‐term forecasts of the SYM‐H index based on 1‐ and 5‐min resolution data. SYMHnet takes, as input, the time series of the parameters' values provided by NASA's Space Science Data Coordinated Archive and predicts, as output, the SYM‐H index value at time point t + w hours for a given time point t where w is 1 or 2. By incorporating Bayesian inference into the learning framework, SYMHnet can quantify both aleatoric (data) uncertainty and epistemic (model) uncertainty when predicting future SYM‐H indices. Experimental results show that SYMHnet works well at quiet time and storm time, for both 1‐ and 5‐min resolution data. The results also show that SYMHnet generally performs better than related machine learning methods. For example, SYMHnet achieves a forecast skill score (FSS) of 0.343 compared to the FSS of 0.074 of a recent gradient boosting machine (GBM) method when predicting SYM‐H indices (1 hr in advance) in a large storm (SYM‐H = −393 nT) using 5‐min resolution data. When predicting the SYM‐H indices (2 hr in advance) in the large storm, SYMHnet achieves an FSS of 0.553 compared to the FSS of 0.087 of the GBM method. In addition, SYMHnet can provide results for both data and model uncertainty quantification, whereas the related methods cannot.

Logical–Mathematical Foundations of a Graph Query Framework for Relational Learning

Relational learning has attracted much attention from the machine learning community in recent years, and many real-world applications have been successfully formulated as relational learning problems. In recent years, several relational learning algorithms have been introduced that follow a pattern-based approach. However, this type of learning model suffers from two fundamental problems: the computational complexity arising from relational queries and the lack of a robust and general framework to serve as the basis for relational learning methods. In this paper, we propose an efficient graph query framework that allows for cyclic queries in polynomial time and is ready to be used in pattern-based learning methods. This solution uses logical predicates instead of graph isomorphisms for query evaluation, reducing complexity and allowing for query refinement through atomic operations. The main differences between our method and other previous pattern-based graph query approaches are the ability to evaluate arbitrary subgraphs instead of nodes or complete graphs, the fact that it is based on mathematical formalization that allows the study of refinements and their complementarity, and the ability to detect cyclic patterns in polynomial time. Application examples show that the proposed framework allows learning relational classifiers to be efficient in generating data with high expressiveness capacities. Specifically, relational decision trees are learned from sets of tagged subnetworks that provide both classifiers and characteristic patterns for the identified classes.

Classifying seismograms using the FastMap algorithm and support-vector machines

Neural networks and related deep learning methods are currently at the leading edge of technologies used for classifying complex objects such as seismograms. However they generally demand large amounts of time and data for model training and their learned models can sometimes be difficult to interpret. FastMapSVM is an interpretable machine learning framework for classifying complex objects, combining the complementary strengths of FastMap with support vector machines (SVMs) and extending the applicability of SVMs to domains with complex objects. FastMap is an efficient linear-time algorithm that maps complex objects to points in a Euclidean space while preserving pairwise domain-specific distances between them. Here we invoke FastMapSVM as a lightweight alternative to neural networks for classifying seismograms. We demonstrate that FastMapSVM outperforms other state-of-the-art methods for classifying seismograms when train data or time is limited. We also show that FastMapSVM can provide an insightful visualization of seismogram clustering behaviour and thus earthquake classification boundaries. We expect FastMapSVM to be viable for classification tasks in many other real-world domains.

Multi-node system modeling and monitoring with extended directed graphical models

Complex manufacturing systems usually contain a large number of variables. Dominated by certain engineering mechanisms, these variables show complicated relationships that cannot be effectively expressed by simple correlation matrices or functions, thus increasing the difficulty of modeling and monitoring these systems. The directed graphical model (DGM) has been used as a flexible tool for describing the relationship among variables in complex systems. However, the DGM treats all variables equally and fails to consider the structural information among them that usually exists. To address this problem, an extended directed graphical model (EDGM) and related parameter estimation, monitoring, and structure learning methods are proposed in this work. Taking prior engineering knowledge into consideration, the EDGM assigns variables into groups and uses groups of variables as nodes in the graph model. By adding hidden state variables to each node, the EDGM can effectively represent the relationship within and between nodes and provide promising monitoring performance. Numerical experiments and a real-world case study of the monocrystalline silicon growth process are performed to verify the effectiveness of the proposed methods.

Education of clinical reasoning in patients with multimorbidity: a scoping review and perspectives for technology-enhanced learning

Multimorbidity is defined as the co-existence of two or more chronic diseases in a patient, and it is increasing in prevalence. This condition poses new problems for clinical reasoning. Few studies inquire regarding the construct of reasoning in multimorbidity and the teaching/learning methods. The objectives of this scoping review were searching for a definition of the construct of clinical reasoning in multimorbidity and the related learning methods, and special ways in which information technology can help. We searched PubMed, Scopus, ERIC and CORE databases. After an iterative process of selection and thematic analysis, we selected 30 articles, that were thematized in three classes: the multimorbid patient as a teacher (8 articles), defining a framework of competence (11 articles), representing multimorbidity and related clinical reasoning (11 articles). In this last theme were also grouped studies using technology to enhance learning. The construct of clinical reasoning in multimorbidity expands over three domains: clinical (including managing uncertainty, anticipating, and detecting evolutions and conflicting guidelines, and setting priorities); relational (concerning communicating uncertainty and developing a feasible, shared plan of care with the patient; organizational) (managing the wide system of resources needed to take care of a multimorbid patient). The preferred teaching methods are based on the encounter with real or expert patients, technology enhanced case-based learning and graphical representations of clinical cases. Perspectives of research should be addressed to permit the learner to experience a patient’s life-long experience by moving forward and back over time while exploring interactions among diseases and social determinants with respect to possibly conflicting treatments. Perspectives on rich, technology-enhanced simulations should be researched.

Simulation, Learning, and Application of Vision-Based Tactile Sensing at Large Scale

Large-scale robotic skin with tactile sensing ability is emerging with the potential for use in close-contact human–robot systems. Although recent developments in vision-based tactile sensing and related learning methods are promising, they have been mostly designed for small-scale use, such as by fingers and hands, in manipulation tasks. Moreover, learning perception for such tactile devices demands a huge tactile dataset, which complicates the data collection process. To address this, this study introduces a multiphysics simulation pipeline, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SimTacLS</i> , which considers not only the mechanical properties of external physical contact but also the realistic rendering of tactile images in a simulation environment. The system utilizes the obtained simulation dataset, including virtual images and skin deformation, to train a tactile deep neural network to extract high-level tactile information. Moreover, we adopt a generative network to minimize sim2real inaccuracy, preserving the simulation-based tactile sensing performance. Last but not least, we showcase this sim2real sensing method for our large-scale tactile sensor ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TacLink</i> ) by demonstrating its use in two trial cases, namely, whole-arm nonprehensile manipulation and intuitive motion guidance, using a custom-built tactile robot arm integrated with TacLink. This article opens new possibilities in the learning of transferable tactile-driven robotics tasks from virtual worlds to actual scenarios without compromising accuracy.

Coarse Mask Guided Interactive Object Segmentation.

Interactive object segmentation aims to produce object masks with user interactions, such as clicks, bounding boxes, and scribbles. Click point is the most popular interactive cue for its efficiency, and related deep learning methods have attracted lots of interest in recent years. Most works encode click points as gaussian maps and concatenate them with images as the model's input. However, the spatial and semantic information of gaussian maps would be noised through multiple convolution layers and won't be fully exploited by top layers for mask prediction. To pass click information to top layers exactly and efficiently, we propose a coarse mask guided model (CMG) which predicts coarse masks with a coarse module to guide the object mask prediction. Specifically, the coarse module encodes user clicks as query features and enriches their semantic information with backbone features through transformer layers, coarse masks are generated based on the enriched query feature and fed into CMG's decoder. Benefiting from the efficiency of transformer, CMG's coarse module and decoder module are lightweight and computationally efficient, making the interaction process more smooth. Experiments on several segmentation benchmarks demonstrate the effectiveness of our method, and we get new state-of-the-art results compared with previous works.

A micro-hyperspectral image classification method of gallbladder cancer based on multi-scale fusion attention mechanism

A micro-hyperspectral image classification method of gallbladder cancer based on multi-scale fusion attention mechanism

Self-Supervised Learning for Heterogeneous Audiovisual Scene Analysis

Due to the difficulty of annotating large amounts of training data, directly learning the association of sound and its makers in natural videos is a challenging task for machines. In this paper, we present a novel audiovisual model that introduces a soft-clustering module as the audio and visual content detector, and regards the pervasive property of audiovisual concurrency as the latent supervision for inferring the correlation among detected contents. Furthermore, we discover for the first time that the complexity of data has an impact on the training efficiency and subsequent performance of audiovisual model, i.e., more complex data brings more obstacles to the model training, and degrades the performance of downstream audiovisual tasks. To address the issue of audiovisual learning, we propose a novel heterogeneous audiovisual scene analysis module that trains the model from simple to complex scene. We show that such ordered learning procedure rewards the model the merits of easy training and fast convergence. Meanwhile, our audiovisual model can also provide effective unimodal representation and cross-modal alignment performance. We further deploy the well-trained model into practical audiovisual sound localization and separation tasks. We show that our localization model significantly outperforms existing methods, based on which we show comparable performance in sound separation task by comparison to several related SOTA audiovisual learning methods without referring external visual supervision.

IMPROVING STUDENT LEARNING OUTCOMES: BRAIN-BASED LEARNING WITH A MIND MAPPING MODEL AFTER THE COVID-19 PANDEMIC

This article examines related learning methods that can attract learners to learn the subjects of the Curriculum with a brain-based learning approach or brain-based Learning. This method uses field research at Muhammadiyah 1 Prambanan Junior High School by interviewing several respondents, namely representatives of 7th-grade students, field observation, and documentation analysis using data in the form of documents and related data sources needed. Data analysis using Miles and Huberman methods is by data collection, data reduction, presentation of data, and withdrawal of conclusions or data verification. The research results show that the learning process with a brain-based learning approach with mind mapping methods significantly impacts learners' learning interest in the subjects of The Islamic Civilization (Tarikh) in Grade 7. The trial results showed that almost all pupils' grade scores increased, affecting average grades in each class. The learners' enthusiasm is also seen when they do mind mapping with great earnestness. However, in this learning model with mind mapping, some shortcomings exist. Namely, it will be difficult for students who are not interested to understand the material quickly.

MRF-Net: A multi-branch residual fusion network for fast and accurate whole-brain MRI segmentation.

Whole-brain segmentation from T1-weighted magnetic resonance imaging (MRI) is an essential prerequisite for brain structural analysis, e.g., locating morphometric changes for brain aging analysis. Traditional neuroimaging analysis pipelines are implemented based on registration methods, which involve time-consuming optimization steps. Recent related deep learning methods speed up the segmentation pipeline but are limited to distinguishing fuzzy boundaries, especially encountering the multi-grained whole-brain segmentation task, where there exists high variability in size and shape among various anatomical regions. In this article, we propose a deep learning-based network, termed Multi-branch Residual Fusion Network, for the whole brain segmentation, which is capable of segmenting the whole brain into 136 parcels in seconds, outperforming the existing state-of-the-art networks. To tackle the multi-grained regions, the multi-branch cross-attention module (MCAM) is proposed to relate and aggregate the dependencies among multi-grained contextual information. Moreover, we propose a residual error fusion module (REFM) to improve the network's representations fuzzy boundaries. Evaluations of two datasets demonstrate the reliability and generalization ability of our method for the whole brain segmentation, indicating that our method represents a rapid and efficient segmentation tool for neuroimage analysis.

Dynamic prototypical feature representation learning framework for semi-supervised skin lesion segmentation

Automated skin lesion segmentation is an essential yet challenging task for computer-aided skin disease diagnosis. One major challenge for learning-based segmentation method is the limited manually annotated dermoscopy images. Many semi-supervised methods are proposed to exploit unlabeled data by self-training with pseudo labels. However, the plain pseudo labels are less accurate and the pixel-wise features of unlabeled data are always not well formulated due to the large variations among different lesions. Aiming at producing a good segmentation embedding space in a semi-supervised manner, in this paper, we propose a novel dynamic prototypical feature representation learning framework to address these problems. Specifically, we propose a novel denoised pseudo label generation method, which effectively filters out the unreliable components in plaint pseudo labels and provides the guidance for the subsequent feature representation learning. Then, we propose a memory relation learning method to enhance the intermediate feature representation globally. Additionally, we propose a prototype-based confidence-aware contrastive learning method to learn a better local feature structure in semi-supervised training, strengthening intra-class compactness and inter-class separability. Extensive experiments on two skin lesion segmentation datasets demonstrate that our method outperforms other popular semi-supervised segmentation methods.

Task-specific contrastive learning for few-shot remote sensing image scene classification

Deep neural network has been successfully applied to remote sensing image scene classification, which requires a large amount of annotated data for training. However, it is time-consuming and labor-intensive to obtain abundant labeled samples in various applications. Therefore, it is of great importance to conduct scene classification with only a few annotated images. In order to address the issue, we propose a task-specific contrastive learning (TSC) model for few-shot scene classification of remote sensing images, which aims to enhance the scene classification performance with fewer labeled samples. Specifically, a self-attention and mutual-attention module (SMAM) is developed to learn feature correlations and reduce the background interference. Moreover, a task-specific contrastive loss function is proposed to optimize the deep network, which generates task-specific paired data based on different views of original images. This strategy has a contribution to enhance the discrimination of features between intra-class and inter-class images. Experimental results on NWPU-RESISC45, WHU-RS19 and UCM datasets demonstrate that the proposed method produces superior accuracies compared with other related few-shot learning methods.

A Constructivist Ontology Relation Learning Method.

From the perspective of philosophy, ontology relations denote ultimate semantic relations of related knowledge concepts. Beyond doubt, it is still a very difficult problem on how to automatically depict and construct ontology relations because of its high abstractness. Some latest research attempted to realize ontology relation learning by learning abstract hierarchies or similarities among knowledge concepts. Inspired by the requirements of associative semantic cognition like in the human brain, a constructivist ontology relation learning (CORL) method is put forward in this study by borrowing the idea of the constructivist learning theory. Wherein, two following points are supposed: 1) each symbol knowledge is looked as a token of representing certain abstract pattern and 2) each pattern denotes a type of relation structures on other patterns, or a directly observed event data, such as physical sensing data, natural image, sound data, text word etc. So, ontology relation could be considered as the associative support degrees from other knowledge concepts to the target concept, which reflects how one knowledge ontology can be demarcated by other knowledge concepts. Then, the knowledge network can be employed to represent an entire domain knowledge system. Meanwhile, an associative random walk mechanism (ARWM) on knowledge network can be considered to explain the semantic generative process of every document. Thus, CORL can be realized by integrating ARWM into an extended latent Dirichlet allocation (LDA) model. Some theoretical and experimental analysis are done. The corresponding results demonstrate that CORL can obtain effective associative semantic relations among concept words, and gain some novel characteristics in better representing knowledge ontology than existing methods.

Forecasting the Disturbance Storm Time Index with Bayesian Deep Learning

The disturbance storm time (Dst) index is an important and useful measurement in space weather research. It has been used to characterize the size and intensity of a geomagnetic storm. A negative Dst value means that the Earth's magnetic field is weakened, which happens during storms. In this paper, we present a novel deep learning method, called the Dst Transformer, to perform short-term, 1-6 hour ahead, forecasting of the Dst index based on the solar wind parameters provided by the NASA Space Science Data Coordinated Archive. The Dst Transformer combines a multi-head attention layer with Bayesian inference, which is capable of quantifying both aleatoric uncertainty and epistemic uncertainty when making Dst predictions. Experimental results show that the proposed Dst Transformer outperforms related machine learning methods in terms of the root mean square error and R-squared. Furthermore, the Dst Transformer can produce both data and model uncertainty quantification results, which can not be done by the existing methods. To our knowledge, this is the first time that Bayesian deep learning has been used for Dst index forecasting.

Ethics and Well-Being: The Health Professions and the COVID-19 Pandemic.

The COVID-19 pandemic has had a profound impact on health professionals, adding to the moral suffering and burnout that existed prepandemic. The physical, psychological, and moral toll of the pandemic has threatened the well-being and integrity of clinicians. The narrative of self-sacrifice and heroism bolstered people early on but was not sustainable over time. For health professions students, the learning environment changed dramatically, limiting opportunities in direct patient care and raising concerns for meeting training requirements. Learners lost social connections and felt isolated while learning remotely, and they witnessed ethical tensions between patient-centered care and parallel obligations to public health. Worries about transmission of the virus and uncertainty about its management contributed to their moral suffering. Educators adjusted curricula to address the changing ethical landscape. Preparing learners for the realities of their future professional identities requires creation of interprofessional moral communities that provide support and help develop the moral agency and integrity of its members using experiential and relational learning methods. Investing in the well-being and resilience of clinicians, implementing the recommendations of the National Academy of Medicine, and engaging learners and faculty as cocreators of ethical practice have the potential to transform the learning environment. Faculty need to be trained as effective mentors to create safe spaces for exploring challenges and address moral adversity. Ethics education will need to expand to issues related to health systems science, social determinants of health, and public health, and the cultivation of moral sensitivity, character development, professional identity formation, and moral resilience.