Learning Supervision Research Articles

Design of Intelligent Control Under Machine Learning Supervision and Signal Compression Mechanism Design for NCSs Under DoS Attacks

Design of Intelligent Control Under Machine Learning Supervision and Signal Compression Mechanism Design for NCSs Under DoS Attacks

Super‐resolution reconstruction algorithm for medical images by fusion of wavelet transform and multi‐scale adaptive feature selection

AbstractConventional computed tomography (CT) images often suffer from blurred edges and unclear details. Image super‐resolution methods can significantly enhance CT image quality, thereby improving diagnostic accuracy. To better extract detailed features and enhance the cascading effects of different feature levels, we propose a novel medical image super‐resolution algorithm that integrates discrete wavelet transform and multi‐scale adaptive feature selection. Our approach uses both the low‐resolution image and its high‐frequency component from the frequency domain as network inputs, with the high‐frequency component providing learning supervision, which enhances detail fidelity in reconstruction. Additionally, we introduce a multi‐scale adaptive feature selection module to learn from different layers of CT images and their inter‐layer correlations. Finally, the pixel information is efficiently integrated by a coordinate attention mechanism incorporating the concept of squeeze excitation. Experimental results show that our method outperforms state‐of‐the‐art methods, achieving superior reconstruction at scale factors of 2, 4, and 8, especially at scale factor 8, where it surpasses others by 1.12 in PSNR, 0.0145 in SSIM, and 0.0038 in LPIPS. Visually, our method also delivers more accurate details and better perceptual quality.

Reference-then-supervision framework for infrared and visible image fusion

Infrared and visible image fusion has drawn increasing attention of researchers in recent years, wherein the complementary information between two source images is extracted to synthesize a new fusion image with richer information. Deep neural network is the latest technique to tackle various image fusion problems. However, the natural absence of ground truth makes it very challenging to optimize deep learning models. While the current methods mainly consider to uses the two source images themselves or their visual features, to provide supervision for learning, which is easy to result in the imbalance between detail preservation and brightness distribution. To boost the performance of the fusion models, it is meaningful and necessary to establish a flexible framework that can combine the advantages of existing models to produce reliable supervision for model training. In this work, we propose a novel reference-then-supervision framework, which aims to fully leverage and exploit the available favorable reference information based on the performance of existing methods and then construct high-quality reliable supervision to assist in model building. For this purpose, we design an automatic filter to produce favorable reference and devise an adaptive enhancement method to construct reliable supervision, which helps to aggregate the advantages of various existing fusion methods for yielding visually pleasing results adapting to different complex scenarios. Extensive experiments on two commonly used datasets and our built challenging test set demonstrate that our framework can greatly improve the performance of existing fusion methods. Ablation study and empirical analysis also present the efficacy of our framework design. Furthermore, the applications on downstream pedestrian detection and object tracking tasks indicate the great potential of our framework. Our code and data are publicly available at https://github.com/zhenglab/ReferenceSupervisionIVIF.

PELAKSANAAN FUNGSI MANAJEMEN SEKOLAH MENENGAH ATAS

School-based management is a school management system that grants authority and power to the institution to manage its operations in line with its potential, demands, and needs. A school is an institution that has the independent authority to establish educational programs (curriculum) and their implications for various school policies in accordance with the school's vision, mission, and educational goals. The aim of this study is to understand and analyze the functions of school management in Senior High Schools. The implementation of school management has been carried out through learning planning, learning implementation, and learning supervision. The learning objectives provide an overview of the relevance and activities to be carried out; the teaching and learning implementation is closely tied to the dimension of human resources, encompassing the number of teachers, educational qualifications, curriculum, library, and more. Furthermore, the supervision of teaching and learning is conducted by the principal in cooperation with the school’s teachers’ council, as well as by the Branch Office of Education both directly and indirectly. Therefore, the implementation of Senior High School Management functions can be concluded as a guideline for conducting learning activities to improve the quality of education. Additionally, alumni and the community should support teaching and learning activities as a form of participation in enhancing the quality of education.

MAIANet: Signal modulation in cassava leaf disease classification

Cassava is the third largest source of carbohydrates for human consumption worldwide; however, it is highly susceptible to viral and bacterial diseases, which pose a significant threat to food security. The advancement of deep learning algorithms in precision agriculture holds the key to enabling the early classification of plant diseases, thereby leading to enhanced crop yields and ultimately stabilizing food security. In the coarse-grained label discrimination task of weak supervision learning, high-quality semantic features contain abundant semantic description information, which plays a crucial role in constructing a precise description of plant disease discrimination in tanglesome field circumstances and directly influences the performance of neural networks. Thus, a multiattention IBN anti-aliasing neural network (MAIANet) was proposed to improve the classification accuracy of cassava leaf disease classification by improving the feature quality in the coarseness label classification task. The proposed MAIANet neural network includes two innovative approaches. First, the multiattention method was designed to scale the feature signals twice to adjust the angular frequency of the feature signals in the residual branch for optimal feature fitting within the residual unit. Second, the anti-aliasing block extracts the high-frequency component feature and optimizes the quantization result of the pooling operation to depress the aliasing signal in the down-sampled feature maps. When the proposed method was tested and validated on the cassava dataset, the results showed that the prediction accuracy of the proposed method significantly improved, with an accuracy of 95.83 %, a loss of 1.720, and an F1-score of 0.9585, outperforming V2-ResNet-101, EfficientNet-B5, RepVGG-B3g4, and AlexNet with significant margins. Based on the above experimental results, the proposed algorithm is suitable for classifying cassava leaf diseases.

Cross-Modality Medical Image Segmentation via Enhanced Feature Alignment and Cross Pseudo Supervision Learning.

Given the diversity of medical images, traditional image segmentation models face the issue of domain shift. Unsupervised domain adaptation (UDA) methods have emerged as a pivotal strategy for cross modality analysis. These methods typically utilize generative adversarial networks (GANs) for both image-level and feature-level domain adaptation through the transformation and reconstruction of images, assuming the features between domains are well-aligned. However, this assumption falters with significant gaps between different medical image modalities, such as MRI and CT. These gaps hinder the effective training of segmentation networks with cross-modality images and can lead to misleading training guidance and instability. To address these challenges, this paper introduces a novel approach comprising a cross-modality feature alignment sub-network and a cross pseudo supervised dual-stream segmentation sub-network. These components work together to bridge domain discrepancies more effectively and ensure a stable training environment. The feature alignment sub-network is designed for the bidirectional alignment of features between the source and target domains, incorporating a self-attention module to aid in learning structurally consistent and relevant information. The segmentation sub-network leverages an enhanced cross-pseudo-supervised loss to harmonize the output of the two segmentation networks, assessing pseudo-distances between domains to improve the pseudo-label quality and thus enhancing the overall learning efficiency of the framework. This method's success is demonstrated by notable advancements in segmentation precision across target domains for abdomen and brain tasks.

Carrying The CRT Legacy in Perilous Times: Research and Practice in the Social Sciences Under Florida’s Stop WOKE Act

Florida’s House Bill 7, also known as the Stop Woke Act, is one of the most controversial legal measures in educational history, increasing the supervision of teaching and learning about antiblack racism in social studies education. Florida Governor, Ron DeSantis, has legally banned the teaching of CRT (critical race theory) from K-12 schools, colleges, and universities. In this paper, I analyze specific points from Florida’s House Bill 7 (2022), unpacking its legal divisiveness that upholds white supremacy in the social sciences. This blatant denial of America’s tragic racial history has intensified a hostile and superficial learning environment for teachers of social studies education. As a Black woman, educator, and researcher; there is an added layer of betrayal teaching about race under intense legal scrutiny. In this article, I intend to unpack my experience as one of the last groups of doctoral students to learn CRT at a Florida public university; revisiting the political shift against CRT and how it has impacted my research and practice.

The Effect of Learning Supervision, Professional Competency and Pedagogical Competency on Elementary Teacher Performance

This research aims to determine the effect of: (1) learning supervision on pedagogical competence; (2) supervision of learning regarding professional competencies; (3) learning supervision of performance competencies; (4) pedagogical competence on performance; (5) professional competence on performance; (6) supervision of learning towards performance through professional competence; and (7) supervision of learning towards performance through pedagogical competence. This research is quantitative, using the path analysis method. There is a population of 168 elementary school teachers in Tiga Lingga District. Slovin's sample was 116 people. The research hypothesis was tested using simultaneous and partial analyses. The research results show that: (1) there is an influence of learning supervision on professional competence; (2) there is an influence of learning supervision on pedagogical competence; (3) there is an influence of learning supervision on performance; (4) there is an influence of professional competence on performance; (5) there is an influence of pedagogical competence on performance; (6) Learning supervision has a positive effect on teacher performance through professional competence, meaning the contribution of the influence of learning supervision on teacher performance through professional competence. The contribution of the effect of learning supervision on teacher performance through pedagogical competence.

Innovative Approach: The Role Of Counseling Guidance Teachers Through Zoom Meetings In Improving Learning Guidance And Learning Supervision For Vocational School Students In Jember

students who are less controlled in their relationships so there is a need for guidance and supervision in learning by counseling teachers. The role of the counseling teacher using Zoom Meeting Media shows the importance of context in the association known to students and the process of coaching to supervision by the students themselves so that the concepts received by students are more meaningful. This research is in the form of causal quantitative (causality quantitative) with the research subject of class X students of SMK Plus Bustanul Ma'arif Gumukmas in the 2023/2024 academic year. The purpose of this study is to increase the role of counseling teachers with Zoom Meeting media in improving the guidance and supervision of grade X students' learning. The data in this study are quantitative data obtained from tests of student knowledge and understanding through questionnaire tests. The results of this study indicate: the influence of the role of the counseling teacher by using Zoom Meeting media on student learning coaching is 78.8%, the influence of the role of the counseling teacher by using Zoom Meeting media on student learning supervision is 70.6%, and the influence of the role of the counseling teacher in using Zoom Meeting media on student learning coaching and supervision together is 79.8%. This means that the application of the counseling teacher's role approach in coaching and supervising students has a significant effect.

TractoSCR: a novel supervised contrastive regression framework for prediction of neurocognitive measures using multi-site harmonized diffusion MRI tractography.

Neuroimaging-based prediction of neurocognitive measures is valuable for studying how the brain's structure relates to cognitive function. However, the accuracy of prediction using popular linear regression models is relatively low. We propose a novel deep regression method, namely TractoSCR, that allows full supervision for contrastive learning in regression tasks using diffusion MRI tractography. TractoSCR performs supervised contrastive learning by using the absolute difference between continuous regression labels (i.e., neurocognitive scores) to determine positive and negative pairs. We apply TractoSCR to analyze a large-scale dataset including multi-site harmonized diffusion MRI and neurocognitive data from 8,735 participants in the Adolescent Brain Cognitive Development (ABCD) Study. We extract white matter microstructural measures using a fine parcellation of white matter tractography into fiber clusters. Using these measures, we predict three scores related to domains of higher-order cognition (general cognitive ability, executive function, and learning/memory). To identify important fiber clusters for prediction of these neurocognitive scores, we propose a permutation feature importance method for high-dimensional data. We find that TractoSCR obtains significantly higher accuracy of neurocognitive score prediction compared to other state-of-the-art methods. We find that the most predictive fiber clusters are predominantly located within the superficial white matter and projection tracts, particularly the superficial frontal white matter and striato-frontal connections. Overall, our results demonstrate the utility of contrastive representation learning methods for regression, and in particular for improving neuroimaging-based prediction of higher-order cognitive abilities. Our code will be available at: https://github.com/SlicerDMRI/TractoSCR.

Analisis Pelaksanaan Program Guru Penggerak Pada Pembelajaran Berdiferensiasi Dalam Mewujudkan Mutu Pendidikan Di SMP Negeri 5 Kebumen

This study aims to analyze planning, organizing, implementing, monitoring, and evaluating, as well as the effectiveness of Program Guru Penggerak on differentiated learning in improving the quality of education. This type of research uses a qualitative approach method. The research was conducted at SMP Negeri 5 Kebumen, Kebumen District, and Kebumen Regency. Data collection techniques include interviews, observation, and document studies. Data analysis techniques through the stages of data collection, data reduction, data presentation, and data verification. The results of this study indicate that: 1) Planning, organizing, implementing, monitoring, and evaluating the Program Guru Penggerak in differentiated learning is based on the competency of the mobilizing teacher in leading learning that is pro-student in the good category; (2) The teacher-driven program on differentiated learning is effective in realizing the quality of education, which is marked by increased student learning outcomes; the results of supervision of learning by the school principal are in the "good" category; and the results of teacher reflection on learning are in the "good" category.

Collaborative learning of supervision and correlation for generalized zero-shot extreme multi-label learning

Collaborative learning of supervision and correlation for generalized zero-shot extreme multi-label learning

Multi-granularity learning of explicit geometric constraint and contrast for label-efficient medical image segmentation and differentiable clinical function assessment

Automated segmentation is a challenging task in medical image analysis that usually requires a large amount of manually labeled data. However, most current supervised learning based algorithms suffer from insufficient manual annotations, posing a significant difficulty for accurate and robust segmentation. In addition, most current semi-supervised methods lack explicit representations of geometric structure and semantic information, restricting segmentation accuracy. In this work, we propose a hybrid framework to learn polygon vertices, region masks, and their boundaries in a weakly/semi-supervised manner that significantly advances geometric and semantic representations. Firstly, we propose multi-granularity learning of explicit geometric structure constraints via polygon vertices (PolyV) and pixel-wise region (PixelR) segmentation masks in a semi-supervised manner. Secondly, we propose eliminating boundary ambiguity by using an explicit contrastive objective to learn a discriminative feature space of boundary contours at the pixel level with limited annotations. Thirdly, we exploit the task-specific clinical domain knowledge to differentiate the clinical function assessment end-to-end. The ground truth of clinical function assessment, on the other hand, can serve as auxiliary weak supervision for PolyV and PixelR learning. We evaluate the proposed framework on two tasks, including optic disc (OD) and cup (OC) segmentation along with vertical cup-to-disc ratio (vCDR) estimation in fundus images; left ventricle (LV) segmentation at end-diastolic and end-systolic frames along with ejection fraction (LVEF) estimation in two-dimensional echocardiography images. Experiments on nine large-scale datasets of the two tasks under different label settings demonstrate our model’s superior performance on segmentation and clinical function assessment.

Multi-scale adversarial learning with difficult region supervision learning models for primary tumor segmentation

Objective. Recently, deep learning techniques have found extensive application in accurate and automated segmentation of tumor regions. However, owing to the variety of tumor shapes, complex types, and unpredictability of spatial distribution, tumor segmentation still faces major challenges. Taking cues from the deep supervision and adversarial learning, we have devised a cascade-based methodology incorporating multi-scale adversarial learning and difficult-region supervision learning in this study to tackle these challenges. Approach. Overall, the method adheres to a coarse-to-fine strategy, first roughly locating the target region, and then refining the target object with multi-stage cascaded binary segmentation which converts complex multi-class segmentation problems into multiple simpler binary segmentation problems. In addition, a multi-scale adversarial learning difficult supervised UNet (MSALDS-UNet) is proposed as our model for fine-segmentation, which applies multiple discriminators along the decoding path of the segmentation network to implement multi-scale adversarial learning, thereby enhancing the accuracy of network segmentation. Meanwhile, in MSALDS-UNet, we introduce a difficult region supervision loss to effectively utilize structural information for segmenting difficult-to-distinguish areas, such as blurry boundary areas. Main results. A thorough validation of three independent public databases (KiTS21, MSD’s Brain and Pancreas datasets) shows that our model achieves satisfactory results for tumor segmentation in terms of key evaluation metrics including dice similarity coefficient, Jaccard similarity coefficient, and HD95. Significance. This paper introduces a cascade approach that combines multi-scale adversarial learning and difficult supervision to achieve precise tumor segmentation. It confirms that the combination can improve the segmentation performance, especially for small objects (our codes are publicly availabled on https://zhengshenhai.github.io/).

Academic support through tutoring, guided learning, and learning diaries in the context of the COVID-19 pandemic: an experimental model for master’s students

IntroductionEngaging students in co-planning their learning paths, peer cooperation, tutoring, and network building in an inclusive and project-based environment has been associated with higher academic and professional success. However, university teachers face challenges in offering guidance and academic supervision to optimize student learning, particularly in the context of online learning. This study aimed to investigate the effectiveness of adapting collaborative learning environments, peer tutoring, and academic supervision in the online learning space.MethodsAn experimental design methodology was employed to investigate the impact of collaborative learning environments, peer tutoring, and academic supervision on student engagement, interest, and dedication to learning.ResultsThe findings showed direct positive effects on the level of engagement (VI; M = 23.18, SD = 5), higher interest and dedication to the learning process (DE: M = 26.93, SD = 3.21), and better concentration and enthusiasm while studying (AB, M = 24.83, SD = 8.52).DiscussionThe results suggest that adapting to online learning by providing collaborative learning environments, peer tutoring, and academic supervision can enhance student engagement and motivation. Further research is needed to explore the long-term effects and scalability of these interventions in diverse educational contexts.

The Principal’s Efforts in Implementing Coaching-Based Academic Supervision for Mobilizing Teachers

The aim of this research is to describe the coaching-based academic supervision model used by school principals to improve teacher’s professional abilities. Apart from that, it is known how well the driving teacher instructors apply learning tips in coaching-based academic supervision in schools. It is an effort to improve the quality of teachers and maintain the quality of the process, which can be achieved by optimizing the role of the school principal as an academic supervisor. This research was conducted using a qualitative approach and the descriptive method with data collection techniques of observation, interviews, and documentation. This model aims to increase the competency of teachers in implementing coaching-based academic supervision activities using pre-supervision, supervision, and post-supervision stages in schools. The model developed and implemented in coaching-based supervision uses the GPAR (Goal, Problem Identification, Action Plans, and Responsibilities) model, namely goals, identification, action plans, and responsibilities, namely preparation for learning supervision and counselling management. A model developed with passion, independence, and teaching. With the help of learning guidance based on the GPAR Coaching model, it should be easier for school principals to communicate with driving teachers so that the teacher’s possibilities in implementing learning activities can be explained well. This can be seen in the results of increasing initial supervision and final supervision scores, which show that the effectiveness between school principals and driving teachers is increasing. The main results of this research show that there are problems with academic supervision based on coaching for driving teachers and school principals, such as supervision by the principal and lack of follow-up by the principal. Additional assistance can help teachers improve their presentations.

PKSEA-Net: A prior knowledge supervised edge-aware multi-task network for retinal arteriolar morphometry

Retinal fundus images serve as a non-invasive modality to obtain information pertaining to retinal vessels through fundus photography, thereby offering insights into cardiovascular and cerebrovascular diseases. Retinal arteriolar morphometry has emerged as the most convenient and fundamental clinical methodology in the realm of patient screening and diagnosis. Nevertheless, the analysis of retinal arterioles is challenging attributable to imaging noise, stochastic fuzzy characteristics, and blurred boundaries proximal to blood vessels. In response to these limitations, we introduce an innovative methodology, named PKSEA-Net, which aims to improve segmentation accuracy by enhancing the perception of edge information in retinal fundus images. PKSEA-Net employs the universal architecture PVT-v2 as the encoder, complemented by a novel decoder architecture consisting of an Edge-Aware Block (EAB) and a Pyramid Feature Fusion Module (PFFM). The EAB block incorporates prior knowledge for supervision and multi-query for multi-task learning, with supervision information derived from an enhanced Full Width at Half Maximum (FWHM) algorithm and gradient map. Moreover, PFFM efficiently integrates multi-scale features through a novel attention fusion method. Additionally, we have collected a Retinal Cross-Sectional Vessel (RCSV) dataset derived from approximately 200 patients in Quzhou People’s Hospital to serve as the benchmark dataset. Comparative evaluations with several state-of-the-art (SOTA) networks confirm that PKSEA-Net achieves exceptional experimental performance, thereby establishing its status as a SOTA approach for precise boundary delineation and retinal vessel segmentation.

Value of a blended learning supervision course at the advanced level: Supervisors’ experiences

Aim: To explore what experiences specialist nurses and midwives have with a blended learning course (digital course component one and physical course component two) to develop their supervisory competence. Methods: A qualitative descriptive design with two focus group interviews (n=9) and written reflections from participants (n=70) from five courses conducted in 2021 and 2022. Findings: Thematic analysis revealed two main themes: 1) The value of blended learning in a clinical supervision course and 2) Areas for improvement. Participants experienced a profound learning outcome through the acquisition of theoretical knowledge digitally during part one of the course, followed by in-person engagement in simulation-based learning activities in part two. Specifically, the participants gained a heightened awareness of the complexity of supervision and increased confidence in using communication tools through simulation. The challenges faced in the digital part of the course highlighted the need for technical improvements, emphasizing the importance of improving flexibility and development of an application for easy access to learning resources. Conclusion: The findings indicate that the blended learning approach enhanced supervision competence. The online component facilitated a more profound learning experience in the in-person simulation-based course. Recommendations for improvement centered on simplifying content and introducing greater flexibility and accessibility in the digital part of the course.

Decoupling semantic and localization for semantic segmentation via magnitude-aware and phase-sensitive learning

Semantic segmentation requires the simultaneous generation of strong semantic and precise localization segmentation results. However, their inherent paradox drives most existing methods to perform trade-offs or overcompensation between high-level semantics and fine localization during resolution reconstruction, which may lead to limited performance or enormous computation costs. To this end, inspired by the frequency model of natural images, we propose a new encoder–decoder-based segmentation architecture, namely MPLSeg, from a novel perspective: semantic-localization decoupled representation via magnitude-aware and phase-sensitive learning. Specifically, we first investigate and reveal the symmetric inverse inherent properties of image magnitude and phase in semantics and localization. Then, building upon that, we construct a concise adaptive frequency-aware module (AFM) to alleviate the semantic gap and spatial location misalignment during multi-level feature fusion. The core of AFM comprises a magnitude perceptron (MP) equipped with the dynamic magnitude weighting mechanism and a phase amender (PA) designed with a spectral residual mapping for keeping sensitive to salient frequency combinations and off-norm localization features, respectively. Finally, we tailor a phase-sensitive loss (PSL) as an auxiliary supervision for semantic-independent proto-localization learning. The PSL ensures multi-level feature diversity and enhances fine-grained resolution reconstruction. Extensive experimental results demonstrate the effectiveness and superiority of MPLSeg and its components. Without any fancy tricks, MPLSeg exhibits the state-of-the-art performance on three challenging semantic segmentation benchmarks. The code is available at https://github.com/qyan0131/MPLSeg.

Development of Learning Supervision Model Website Based on Improving Teacher Performance at Elementary School

This research aims to produce products and test the feasibility of products, such as producing a website-based supervision model development system in improving teacher performance in elementary schools, to facilitate the management of conventional/manual supervision of website-based management information systems and determine the feasibility of website-based learning supervision system models in improving teacher performance in elementary schools. The method used in this research is Research and Development (R&D). The research steps include 1) data information, 2) model design, 3) model testing, 4) model revision, 5) development, 6) trial/testing, 7) model revision, 8) finalization and socialization. This research was conducted in a participatory manner. The research output targets at this stage are preparing a website-based learning supervision model design. This website-based principal learning supervision model design has been tested and revised to obtain an effective learning supervision model and develop a website-based learning supervision model. The results of this research are: (1) Learning supervision activities are carried out through the website http://supervisipbelajaran.educmps.com, (2) Principals feel greatly helped by the Website-Based Supervision Model because it is practical, effective, and efficient, (3) Making it easier for teachers to improve performance at school.