Efficient Learning Research Articles

포스트 코로나 시대의 간호대학생이 추구하는 교수학습법 유형

Objectives The purpose of this study was to understand the characteristics of each type of nursing students by examining and categorizing the perception structure of nursing students through Q methodology and to present strategies for developing nursing education programs to apply and improve teaching and learning methods. Methods In order to organize the method Q population, a written interview on the facilitation teaching and learning method experienced by nursing students and a literature review related to the facilitation teaching and learning method were conducted. Based on the results derived through this, a total of 34 Q statements were extracted through the process of selecting duplicate or ambiguous sentences. Q Sample statements were classified into a normal distribution table on a 9-point scale by 40 nursing college students, and the data collected through this were analyzed using the pc-QUANAL program. Results As a result of the analysis of the results, five types of perception of facilitation teaching and learning meth-ods experienced by liver nursing college students were identified. The first type was an autonomous and demo-cratic class atmosphere pursuit type, the second type was a clear lecture content delivery wish type, the third type was an efficient teaching and learning method pursuit type, and the fourth type was a learner-customized teach-ing and learning method pursuit type. Conclusions Through this study, it is expected that nursing universities will be an opportunity to apply educational media and educational tools of nursing education to develop nursing education programs that effectively apply the Facilitation Teaching and Learning Method. In addition, it can be used as basic data for the development of educa-tional media that helps to conduct high-quality nursing education.

Interpretable machine learning framework to predict gout associated with dietary fiber and triglyceride-glucose index

BackgroundGout prediction is essential for the development of individualized prevention and treatment plans. Our objective was to develop an efficient and interpretable machine learning (ML) model using the SHapley Additive exPlanation (SHAP) to link dietary fiber and triglyceride-glucose (TyG) index to predict gout.MethodsUsing datasets from the National Health and Nutrition Examination Survey (NHANES) (2005–2018) population to study dietary fiber, the TyG index was used to predict gout. After evaluating the performance of six ML models and selecting the Light Gradient Boosting Machine (LGBM) as the optimal algorithm, we interpret the LGBM model for predicting gout using SHAP and reveal the decision-making process of the model.ResultsAn initial survey of 70,190 participants was conducted, and after a gradual exclusion process, 12,645 cases were finally included in the study. Selection of the best performing LGBM model for prediction of gout associated with dietary fiber and TyG index (Area under the ROC curve (AUC): 0.823, 95% confidence interval (CI): 0.798–0.848, Accuracy: 95.3%, Brier score: 0.077). The feature importance of SHAP values indicated that age was the most important feature affecting the model output, followed by uric acid (UA). The SHAP values showed that lower dietary fiber values had a more pronounced effect on the positive prediction of the model, while higher values of the TyG index had a more pronounced effect on the positive prediction of the model.ConclusionThe interpretable LGBM model associated with dietary fiber and TyG index showed high accuracy, efficiency, and robustness in predicting gout. Increasing dietary fiber intake and lowering the TyG index are beneficial in reducing the potential risk of gout.

A rehearsal framework for computational efficiency in online continual learning

AbstractIn the realm of online continual learning, models are expected to adapt to an ever-changing environment. One of the most persistent hurdles in this adaptation is the mitigation of a phenomenon called "Catastrophic Forgetting" (CF). This critical condition occurs when models trained on non-identically distributed data lose performance in previously learned tasks. Rehearsal methods, leveraging the ability to replay older samples, aim to address this challenge by incorporating a buffer of past training samples. However, the absence of known task boundaries complicates the adaptation of current CF mitigation methods. This paper proposes a method attuned to data stream characteristics and online model performance in a resource-constrained environment. The number of training iterations and learning rate emerges as crucial hyperparameters, impacting the efficacy and efficiency of online continual learning. Up to this point, we propose a combination of Experience Replay methodologies, a Drift Detector, and various training convergence policies, specially tailored for scenarios with unknown task boundaries. Experimental results demonstrate the effectiveness of our approach, maintaining or enhancing performance compared to baseline methods, while significantly improving computational efficiency.

Analysis of Continual Learning Techniques for Image Generative Models with Learned Class Information Management

The advancements in deep learning have significantly enhanced the capability of image generation models to produce images aligned with human intentions. However, training and adapting these models to new data and tasks remain challenging because of their complexity and the risk of catastrophic forgetting. This study proposes a method for addressing these challenges involving the application of class-replacement techniques within a continual learning framework. This method utilizes selective amnesia (SA) to efficiently replace existing classes with new ones while retaining crucial information. This approach improves the model’s adaptability to evolving data environments while preventing the loss of past information. We conducted a detailed evaluation of class-replacement techniques, examining their impact on the “class incremental learning” performance of models and exploring their applicability in various scenarios. The experimental results demonstrated that our proposed method could enhance the learning efficiency and long-term performance of image generation models. This study broadens the application scope of image generation technology and supports the continual improvement and adaptability of corresponding models.

PODE: privacy-enhanced distributed federated learning approach for origin-destination estimation

The statewide consumer transportation demand model analyzes consumers’ transportation needs and preferences within a particular state. It involves collecting and analyzing data on travel behavior, such as trip purpose, mode choice, and travel patterns, and using this information to create models that predict future travel demand. Naturalistic research, crash databases, and driving simulations have all contributed to our knowledge of how modifications to vehicle design affect road safety. This study proposes an approach named PODE that utilizes federated learning (FL) to train the deep neural network to predict the truck destination state, and in the context of origin-destination (OD) estimation, sensitive individual location information is preserved as the model is trained locally on each device. FL allows the training of our DL model across decentralized devices or servers without exchanging raw data. The primary components of this study are a customized deep neural network based on federated learning, with two clients and a server, and the key preprocessing procedures. We reduce the number of target labels from 51 to 11 for efficient learning. The proposed methodology employs two clients and one-server architecture, where the two clients train their local models using their respective data and send the model updates to the server. The server aggregates the updates and returns the global model to the clients. This architecture helps reduce the server’s computational burden and allows for distributed training. Results reveal that the PODE achieves an accuracy of 93.20% on the server side.

An Efficient Hybrid Deep Learning Framework for Predicting Student Academic Performance

An Efficient Hybrid Deep Learning Framework for Predicting Student Academic Performance

Efficient Deformation Learning of Varied Garments with a Structure-Preserving Multilevel Framework

Due to the highly nonlinear behavior of clothing, modelling fine-scale garment deformation on arbitrary meshes under varied conditions within a unified network poses a significant challenge. Existing methods often compromise on either model generalization, deformation quality, or runtime speed, making them less suitable for real-world applications. To address it, we propose to incorporate multi-source graph construction and pooling to achieve a novel graph learning scheme. We first introduce methods for extracting cues from different deformation correlations and transform the garment mesh into a comprehensive graph enriched with deformation-related information. To enhance the learning capability and generalizability of the model, we present structure-preserving pooling and unpooling strategies for the mesh deformation task, thereby improving information propagation across the mesh and enhancing the realism of deformation. Lastly, we conduct an attribution analysis and visualize the contribution of various vertices in the graph to the output, providing insights into the deformation behavior. The experimental results demonstrate superior performance against state-of-the-art methods.

AARF: Autonomous Attack Response Framework for Honeypots to Enhance Interaction Based on Multi-Agent Dynamic Game

Highly interactive honeypots can form reliable connections by responding to attackers to delay and capture intranet attacks. However, current research focuses on modeling the attacker as part of the environment and defining single-step attack actions by simulation to study the interaction of honeypots. It ignores the iterative nature of the attack and defense game, which is inconsistent with the correlative and sequential nature of actions in real attacks. These limitations lead to insufficient interaction of the honeypot response strategies generated by the study, making it difficult to support effective and continuous games with attack behaviors. In this paper, we propose an autonomous attack response framework (named AARF) to enhance interaction based on multi-agent dynamic games. AARF consists of three parts: a virtual honeynet environment, attack agents, and defense agents. Attack agents are modeled to generate multi-step attack chains based on a Hidden Markov Model (HMM) combined with the generic threat framework ATT&CK (Adversarial Tactics, Techniques, and Common Knowledge). The defense agents iteratively interact with the attack behavior chain based on reinforcement learning (RL) to learn to generate honeypot optimal response strategies. Aiming at the sample utilization inefficiency problem of random uniform sampling widely used in RL, we propose the dynamic value label sampling (DVLS) method in the dynamic environment. DVLS can effectively improve the sample utilization during the experience replay phase and thus improve the learning efficiency of honeypot agents under the RL framework. We further couple it with a classic DQN to replace the traditional random uniform sampling method. Based on AARF, we instantiate different functional honeypot models for deception in intranet scenarios. In the simulation environment, honeypots collaboratively respond to multi-step intranet attack chains to defend against these attacks, which demonstrates the effectiveness of AARF. The average cumulative reward of the DQN with DVLS is beyond eight percent, and the convergence speed is improved by five percent compared to a classic DQN.

Efficient Machine Learning Techniques to Classifying Cardiovascular Disease and Improve Prediction Analysis

Cardiovascular Disease (CVD) account for a large portion of the global health burden and are one of the main causes of decease worldwide. In the classification and forecasting of CVDs, Machine Learning (ML) techniques have demonstrated encouraging outcomes. In this research report, a comparative analysis of classification and prediction models for CVD is presented, including both linear and ensemble ML approaches. The paper compares ensemble models like Catboost, Histogram Gradient Boosting Machine (HGBM), and Extra Trees against linear models like Gaussian Nave Bayes, SVM, and KNN. The objective is to identify the most effective CVD prediction model by assessing its performance through accuracy, precision, sensitivity and F1 score as key evaluation metrics. Moreover, results show that ensemble models outperform linear models using advanced techniques such as boosting and histogram-based algorithms. The results underscore the critical role ensemble models play in accurately diagnosing and predicting cardiovascular disease and provide important new information to researchers and healthcare providers. Using these models has the potential to significantly improve patient outcomes and health management by enabling early detection and intervention

Real-time deep-learning-based object detection and unsupervised statistical analysis for quantitative evaluation of defect length direction on magnetooptical faraday effect

Magnetooptical nondestructive inspection (MONDI) is widely used in various industries to detect defects in metal including ferromagnetic materials. Despite its high precision and sensitivity, its inspection accuracy is highly dependent on the direction of the magnetizer. In addition, the irregular shapes of defects make the assessment of their severity challenging. To address these limitations, we propose an efficient real-time deep learning (DL)-based object detection model called the MONDI detector. This model is designed to integrate a DL-based object detection model with statistical analysis based on regression model to classify and quantify the magnetizer direction. To comprehensively assess algorithm performance, this study investigates variations in the excitation field, defect shape, and defect depth. This analysis is expected to contribute to the state-of-the-art object detection paradigm in MONDI system.

Deep Reinforcement Learning for Optimizing Restricted Access Window in IEEE 802.11ah MAC Layer

The IEEE 802.11ah standard is introduced to address the growing scale of internet of things (IoT) applications. To reduce contention and enhance energy efficiency in the system, the restricted access window (RAW) mechanism is introduced in the medium access control (MAC) layer to manage the significant number of stations accessing the network. However, to achieve optimized network performance, it is necessary to appropriately determine the RAW parameters, including the number of RAW groups, the number of slots in each RAW, and the duration of each slot. In this paper, we optimize the configuration of RAW parameters in the uplink IEEE 802.11ah-based IoT network. To improve network throughput, we analyze and establish a RAW parameters optimization problem. To effectively cope with the complex and dynamic network conditions, we propose a deep reinforcement learning (DRL) approach to determine the preferable RAW parameters to optimize network throughput. To enhance learning efficiency and stability, we employ the proximal policy optimization (PPO) algorithm. We construct network environments with periodic and random traffic in an NS-3 simulator to validate the performance of the proposed PPO-based RAW parameters optimization algorithm. The simulation results reveal that using the PPO-based DRL algorithm, optimized RAW parameters can be obtained under different network conditions, and network throughput can be improved significantly.

Efficient learning strategy for predicting glass forming ability in imbalanced datasets of bulk metallic glasses

Efficient learning strategy for predicting glass forming ability in imbalanced datasets of bulk metallic glasses

Analysis of Soil Health Parameters to Identify Important Soil Nutrients and Weights Using Feature Engineering for Multiple Agri-Advices

Introduction:: Identification of important soil nutrients is a very important task for precision farming and developing efficient machine learning models. Method:: The existing work shows that the patent is filed and published on a method and device for assessment of soil health parameters and recommendation of fertilizers. The existing work is done for one advice at a time not for several advices. Multiple advices that are taken into account for the task are appropriate crops, organic fertilizer, and combination 1 and combination 2 of fertilizers. objective: Apply feature selection techniques based on Chi-Square, ANOVA and Mutual Information Gain scoring functions such as Select K Best and Select Percentile for multiple agri-advice dataset of Pune District regions to identify important soil health features to reduce the complexity of classification models and in turn reduce space and the computational time of different classification models. Result:: This paper presented results of feature selection techniques based on Chi-Square, ANOVA and Mutual Information Gain scoring functions such as Select K Best and Select Percentile for multiple agri-advice datasets of Pune District regions to identify important soil health features. Conclusion:: As per Chi-Square, ANOVA and Mutual Information scoring functions with Select K Best and Select Percentile techniques ‘Mn’ was the most important parameter and Cu’ and ‘B’ were the least important parameters among all 11 parameters common in 4 agriculture advices. Whereas Ph, K, Fe, 'OC', 'N', 'S', 'Mn', and 'P' will be used for future research work on the development of an efficient classification algorithm for multi-advice generators.

An efficient deep learning model for tomato disease detection

Tomatoes possess significant nutritional and economic value. However, frequent diseases can detrimentally impact their quality and yield. Images of tomato diseases captured amidst intricate backgrounds are susceptible to environmental disturbances, presenting challenges in achieving precise detection and identification outcomes. This study focuses on tomato disease images within intricate settings, particularly emphasizing four prevalent diseases (late blight, gray leaf spot, brown rot, and leaf mold), alongside healthy tomatoes. It addresses challenges such as excessive interference, imprecise lesion localization for small targets, and heightened false-positive and false-negative rates in real-world tomato cultivation settings. To address these challenges, we introduce a novel method for tomato disease detection named TomatoDet. Initially, we devise a feature extraction module integrating Swin-DDETR’s self-attention mechanism to craft a backbone feature extraction network, enhancing the model’s capacity to capture details regarding small target diseases through self-attention. Subsequently, we incorporate the dynamic activation function Meta-ACON within the backbone network to further amplify the network’s ability to depict disease-related features. Finally, we propose an enhanced bidirectional weighted feature pyramid network (IBiFPN) for merging multi-scale features and feeding the feature maps extracted by the backbone network into the multi-scale feature fusion module. This enhancement elevates detection accuracy and effectively mitigates false positives and false negatives arising from overlapping and occluded disease targets within intricate backgrounds. Our approach demonstrates remarkable efficacy, achieving a mean Average Precision (mAP) of 92.3% on a curated dataset, marking an 8.7% point improvement over the baseline method. Additionally, it attains a detection speed of 46.6 frames per second (FPS), adeptly meeting the demands of agricultural scenarios.

An efficient deep neural network for automatic classification of acute intracranial hemorrhages in brain CT scans

BackgroundRecent advancements in deep learning models have demonstrated their potential in the field of medical imaging, achieving remarkable performance surpassing human capabilities in tasks such as classification and segmentation. However, these modern state-of-the-art network architectures often demand substantial computational resources, which limits their practical application in resource-constrained settings. This study aims to propose an efficient diagnostic deep learning model specifically designed for the classification of intracranial hemorrhage in brain CT scans. MethodOur proposed model utilizes a combination of depthwise separable convolutions and a multi-receptive field mechanism to achieve a trade-off between performance and computational efficiency. The model was trained on RSNA datasets and validated on CQ500 dataset and PhysioNet dataset. ResultThrough a comprehensive comparison with state-of-the-art models, our model achieves an average AUROC score of 0.952 on RSNA datasets and exhibits robust generalization capabilities, comparable to SE-ResNeXt, across other open datasets. Furthermore, the parameter count of our model is just 3 % of that of MobileNet V3. ConclusionThis study presents a diagnostic deep-learning model that is optimized for classifying intracranial hemorrhages in brain CT scans. The efficient characteristics make our proposed model highly promising for broader applications in medical settings.

Adaptive recognition of machining features in sheet metal parts based on a graph class-incremental learning strategy

The integration of computer-aided design (CAD), computer-aided process planning (CAPP), and computer-aided manufacturing (CAM) systems is significantly enhanced by employing deep learning-based automatic feature recognition (AFR) methods. These methods outperform traditional, rule-based approaches, particularly in handling the complexities of intersecting features. However, existing deep learning-based AFR methods face two major challenges. The initial challenge stems from the frequent utilization of voxelized or point-cloud representations of CAD models, resulting in the unfortunate loss of valuable geometric and topological information inherent in original Boundary representation (B-Rep) models. The second challenge involves the limitation of supervised deep learning methods in identifying machining features that are not present in the predefined dataset. This constraint renders them suboptimal for the continually evolving datasets of real industrial scenarios. To address the first challenge, this study introduces a graph-structured language, Multidimensional Attributed Face-Edge Graph (maFEG), crafted to encapsulate the intricate geometric and topological details of CAD models. Furthermore, a graph neural network, Sheet-metalNet, is proposed for the efficient learning and interpretation of maFEGs. To tackle the second challenge, a three-component incremental learning strategy is proposed: an initial phase of pre-training and fine-tuning, a prototype sampling-based replay, and a stage employing knowledge distillation for parameter regularization. The effectiveness of Sheet-metalNet and its complementary incremental learning strategy is evaluated using the open-source MFCAD++ dataset and the newly created SMCAD dataset. Experimental results show that Sheet-metalNet surpasses state-of-the-art AFR methods in machining feature recognition accuracy. Moreover, Sheet-metalNet demonstrates adaptability to dynamic dataset changes, maintaining high performance when encountering newly introduced features, thanks to its innovative incremental learning strategy.

A Method of Skin Disease Detection Using Image Processing and Machine Learning

Skin conditions are prevalent health issues globally. The dangers posed by these infections are unseen, leading to physical discomfort and mental anguish. In severe cases, skin diseases can even progress to skin cancer. Consequently, the identification of skin diseases from clinical images remains a significant challenge in medical image analysis. Furthermore, manual diagnosis by medical professionals is time-consuming and subjective. Therefore, there is a need for automated skin disease prediction to expedite treatment planning for both patients and dermatologists. These studies presents a digital hair removal method and de-blurs or denoise the images. To extract essential patterns from the skin imagesand statistical features techniques are utilized. Two efficient machine learning algorithms, namely Support Vector Machine (SVM), and Convolutional Neural Network (CNN) classifiers, are employed with the extracted features to accurately classify skin images as melanoma (MEL), melanocytic nevus (NV), basal cell carcinoma (BCC), actinic keratosis (AK), benign keratosis (BKL), dermatofibroma (DF), vascular lesion (VASC), and Squamous cell carcinoma (SCC). The models are validated using the ISIC 2019 challenge and HAM10000 datasets, with SVM demonstrating slightly superior performance compared to the other classifiers. Furthermore, a comparison with state-of-the-art methods is conducted to evaluate the effectiveness of the proposed approach.

Controlling chaos using edge computing hardware

Machine learning provides a data-driven approach for creating a digital twin of a system – a digital model used to predict the system behavior. Having an accurate digital twin can drive many applications, such as controlling autonomous systems. Often, the size, weight, and power consumption of the digital twin or related controller must be minimized, ideally realized on embedded computing hardware that can operate without a cloud-computing connection. Here, we show that a nonlinear controller based on next-generation reservoir computing can tackle a difficult control problem: controlling a chaotic system to an arbitrary time-dependent state. The model is accurate, yet it is small enough to be evaluated on a field-programmable gate array typically found in embedded devices. Furthermore, the model only requires 25.0 ±7.0\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm 7.0$$\\end{document} nJ per evaluation, well below other algorithms, even without systematic power optimization. Our work represents the first step in deploying efficient machine learning algorithms to the computing “edge.”

Deep learning-based semantic segmentation for morphological fractography

Fractographic analysis poses a significant challenge for field researchers without specialized training in fractography. To address this issue, this study introduces a comprehensive integrated workflow that encapsulates the entire process from dataset preparation and data enhancement to leveraging the SegFormer model for deep learning-driven semantic segmentation. An extensive collection of fractography images is formulated and augmented to train the SegFormer model, enabling precise semantic segmentation of morphological fracture regions including cleavage, ductile, dimple, fatigue striations, and others. To accommodate the demanding SEM imaging conditions which frequently include distortions, noise, and aberrations, we developed a two-stage method with diverse data augmentation strategies. This method resulted in a robust model demonstrating exceptional performance, as evidenced by a high mean Intersection over Union (mIOU) score of 59.7 and other metrics. The findings validate the potential of deep learning techniques, particularly the SegFormer model's efficacy in morphological fractography image segmentation for the first time. Our work offers a cost-effective, and efficient alternative deep learning approach to traditional experimental fracture analysis, thereby expanding opportunities for a broader range of professionals in the engineering domain.

Physical Prior Mean Function-Driven Gaussian Processes Search for Minimum-Energy Reaction Paths with a Climbing-Image Nudged Elastic Band: A General Method for Gas-Phase, Interfacial, and Bulk-Phase Reactions.

The climbing-image nudged elastic band (CI-NEB) method serves as an indispensable tool for computational chemists, offering insight into minimum-energy reaction paths (MEPs) by delineating both transition states (TSs) and intermediate nonstationary structures along reaction coordinates. However, executing CI-NEB calculations for reactions with extensive reaction coordinate spans necessitates a large number of images to ensure a reliable convergence of the MEPs and TS structures, presenting a computationally demanding optimization challenge, even with mildly costly electronic-structure methods. In this study, we advocate for the utilization of physically inspired prior mean function-based Gaussian processes (GPs) to expedite MEP exploration and TS optimization via the CI-NEB method. By incorporating reliable prior physical approximations into potential energy surface (PES) modeling, we demonstrate enhanced efficiency in multidimensional CI-NEB optimization with surrogate-based optimizers. Our physically informed GP approach not only outperforms traditional nonsurrogate-based optimizers in optimization efficiency but also on-the-fly learns the reaction path valley during optimization, culminating in significant advancements. The surrogate PES derived from our optimization exhibits high accuracy compared to true PES references, aligning with our emphasis on leveraging reliable physical priors for robust and efficient posterior mean learning in GPs. Through a systematic benchmark study encompassing various reaction pathways, including gas-phase, bulk-phase, and interfacial/surface reactions, our physical GPs consistently demonstrate superior efficiency and reliability. For instance, they outperform the popular fast inertial relaxation engine optimizer by approximately a factor of 10, showcasing their versatility and efficacy in exploring reaction mechanisms and surface reaction PESs.