Local Learning Research Articles

Improved FasterViT model for citrus disease diagnosis

Despite advances in deep learning for plant leaf disease recognition, accurately distinguishing morphological features under varying environmental conditions continues to pose significant challenges. Traditional deep learning models often fail to effectively merge local and global information, especially in small-scale datasets, impairing performance and elevating training costs. Focusing on citrus diseases, we propose an improved FasterViT Model, an advanced hybrid CNN-ViT framework that builds upon the FasterViT model. The proposed model seamlessly integrates CNN's rapid local learning capabilities with ViT's global information processing strength, thereby effectively extracting complex textures and morphological features from images. Cross-stage alternating Mixup and Cutout methods are strategically employed to enhance model robustness and generalization capabilities, particularly valuable for fast learning on small-scale datasets by simulating a more diverse training environment. Triplet Attention and AdaptiveAvgPool mechanisms are utilized to reduce training costs and optimize training performance. The proposed model is tested on both our specially constructed small-scale citrus disease dataset called in-field small dataset and the comprehensive PlantVillage dataset. The experimental results demonstrated that the model exhibits the capability of fast learning and adaptation to small sample training in plant disease detection tasks, and demonstrates the effectiveness of our improvement approach in improving model accuracy and reducing training costs. Additionally, its exemplary performance in transfer learning scenarios underscores its adaptability and broad applicability. This study not only highlights the efficacy of the improved FasterViT model in addressing the complexities of plant disease image recognition but also pioneers a new paradigm for developing efficient, scalable, and robust classification systems.

Development of Local Potential-Based Animal Website Learning Media for Senior High School Students

Contextual learning, which integrates learning materials with the students' real environment, can make learning more meaningful for the students. This research aims to assess the feasibility of the Animal Website development product as a learning media. The research adopts the Research and Development (R&D) methodology with the 4D development model (Define, Design, Develop, and Disseminate). However, the developed product only reached the Develop stage. The study was conducted at Senior High School with students from the 11th and 12th grade of the Science Program (MIPA) as the research subjects. Data collection techniques involved interviews and questionnaires, while data analysis employed qualitative and quantitative analysis methods. The validation results the Animal Website learning media, which incorporates animal-related materials based on the local potential of Bangka Island, is of very good quality and highly suitable for use in the learning process.ABSTRAK: Konsep pembelajaran kontekstual yang mengintegrasikan materi pembelajaran dengan lingkungan nyata peserta didik dapat menjadikan pembelajaran peserta didik jadi lebih bermakna. Penelitian ini bertujuan untuk menguji kelayakan produk pengembangan Animal Website sebagai media pembelajaran. Penelitian ini menggunakan metode penelitian Research and Development (R&D) dengan model pengembangan 4D (Define, Design, Develop, and Disseminate. Akan tetapi, produk yang dikembangkan hanya sampai pada tahap Develop. Penelitian dilakukan di MAN (Madrasah aliyah Negeri) dengan subjek penelitian peserta didik kelas XI dan XII MIPA. Teknik pengambilan data berdasarkan wawancara dan angket. Sedangkan, teknik analisis data menggunakan teknik analisis data kualitatif dan kuantitatif. Hasil validasi Animal Website materi animalia berbasis potensi lokal Pulau Bangka memiliki kualitas sangat layak untuk digunakan dalam proses pembelajaran.

The Fagogoru Ethnopedagogy Textbook Development: A Local Learning Resource for Elementary Schools in Central Halmahera

The Fagogoru Ethnopedagogy Textbook Development: A Local Learning Resource for Elementary Schools in Central Halmahera

Identifikasi Sumber Belajar Lokal untuk Mendukung Inovasi Pembelajaran Biologi

This research aims to identify local learning resources as an effort to support innovation in high school biology teaching in Mataram City and West Lombok Regency. This study involves exploration using observation and interviews with teachers and students to collect data on the potential of local learning resources and their application in biology education. The results indicate that there are various potential local learning resources, such as school gardens, city parks, urban forests, coastal areas, and local agro-tourism sites. The identification and utilization of these local learning resources have proven to enhance students' interest and motivation, as well as provide a more contextual and relevant learning experience. Data analysis shows that while there is significant potential in utilizing local learning resources, there are still challenges in its implementation.

Real-Time Deepfake Video Detection Using Eye Movement Analysis with a Hybrid Deep Learning Approach

Deepfake technology uses artificial intelligence to create realistic but false audio, images, and videos. Deepfake technology poses a significant threat to the authenticity of visual content, particularly in live-stream scenarios where the immediacy of detection is crucial. Existing Deepfake detection approaches have limitations and challenges, prompting the need for more robust and accurate solutions. This research proposes an innovative approach: combining eye movement analysis with a hybrid deep learning model to address the need for real-time Deepfake detection. The proposed hybrid deep learning model integrates two deep neural network architectures, MesoNet4 and ResNet101, to leverage their respective architectures’ strengths for effective Deepfake classification. MesoNet4 is a lightweight CNN model designed explicitly to detect subtle manipulations in facial images. At the same time, ResNet101 handles complex visual data and robust feature extraction. Combining the localized feature learning of MesoNet4 with the deeper, more comprehensive feature representations of ResNet101, our robust hybrid model achieves enhanced performance in distinguishing between manipulated and authentic videos, which cannot be conducted with the naked eye or traditional methods. The model is evaluated on diverse datasets, including FaceForensics++, CelebV1, and CelebV2, demonstrating compelling accuracy results, with the hybrid model attaining an accuracy of 0.9873 on FaceForensics++, 0.9689 on CelebV1, and 0.9790 on CelebV2, showcasing its robustness and potential for real-world deployment in content integrity verification and video forensics applications.

Global-local aware Heterogeneous Graph Contrastive Learning for multifaceted association prediction in miRNA-gene-disease networks.

Unraveling the intricate network of associations among microRNAs (miRNAs), genes, and diseases is pivotal for deciphering molecular mechanisms, refining disease diagnosis, and crafting targeted therapies. Computational strategies, leveraging link prediction within biological graphs, present a cost-efficient alternative to high-cost empirical assays. However, while plenty of methods excel at predicting specific associations, such as miRNA-disease associations (MDAs), miRNA-target interactions (MTIs), and disease-gene associations (DGAs), a holistic approach harnessing diverse data sources for multifaceted association prediction remains largely unexplored. The limited availability of high-quality data, as vitro experiments to comprehensively confirm associations are often expensive and time-consuming, results in a sparse and noisy heterogeneous graph, hindering an accurate prediction of these complex associations. To address this challenge, we propose a novel framework called Global-local aware Heterogeneous Graph Contrastive Learning (GlaHGCL). GlaHGCL combines global and local contrastive learning to improve node embeddings in the heterogeneous graph. In particular, global contrastive learning enhances the robustness of node embeddings against noise by aligning global representations of the original graph and its augmented counterpart. Local contrastive learning enforces representation consistency between functionally similar or connected nodes across diverse data sources, effectively leveraging data heterogeneity and mitigating the issue of data scarcity. The refined node representations are applied to downstream tasks, such as MDA, MTI, and DGA prediction. Experiments show GlaHGCL outperforming state-of-the-art methods, and case studies further demonstrate its ability to accurately uncover new associations among miRNAs, genes, and diseases. We have made the datasets and source code publicly available at https://github.com/Sue-syx/GlaHGCL.

Increasing trust in AI through privacy preservation and model explainability: Federated Learning of Fuzzy Regression Trees

Federated Learning (FL) lets multiple data owners collaborate in training a global model without any violation of data privacy, which is a crucial requirement for enhancing users’ trust in Artificial Intelligence (AI) systems. Despite the significant momentum recently gained by the FL paradigm, most of the existing approaches in the field neglect another key pillar for the trustworthiness of AI systems, namely explainability. In this paper, we propose a novel approach for FL of fuzzy regression trees (FRTs), which are generally acknowledged as highly interpretable by-design models. The proposed FL procedure is designed for the scenario of horizontally partitioned data and is based on the transmission of aggregated statistics from the clients to a central server for the tree induction procedure. It is shown that the proposed approach faithfully approximates the ideal case in which the tree induction algorithm is applied on the union of all local datasets, while still ensuring privacy preservation. Furthermore, the FL approach brings benefits, in terms of generalization capability, compared to the local learning setting in which each participant learns its own FRT based only on the private, local, dataset. The adoption of linear models in the leaf nodes ensures a competitive level of performance, as assessed by an extensive experimental campaign on benchmark datasets. The analysis of the results covers both the aspects of accuracy and interpretability of FRT. Finally, we discuss the application of the proposed federated FRT to the task of Quality of Experience forecasting in an automotive case-study.

Paired competing neurons improving STDP supervised local learning in Spiking Neural Networks.

Direct training of Spiking Neural Networks (SNNs) on neuromorphic hardware has the potential to significantly reduce the energy consumption of artificial neural network training. SNNs trained with Spike Timing-Dependent Plasticity (STDP) benefit from gradient-free and unsupervised local learning, which can be easily implemented on ultra-low-power neuromorphic hardware. However, classification tasks cannot be performed solely with unsupervised STDP. In this paper, we propose Stabilized Supervised STDP (S2-STDP), a supervised STDP learning rule to train the classification layer of an SNN equipped with unsupervised STDP for feature extraction. S2-STDP integrates error-modulated weight updates that align neuron spikes with desired timestamps derived from the average firing time within the layer. Then, we introduce a training architecture called Paired Competing Neurons (PCN) to further enhance the learning capabilities of our classification layer trained with S2-STDP. PCN associates each class with paired neurons and encourages neuron specialization toward target or non-target samples through intra-class competition. We evaluate our methods on image recognition datasets, including MNIST, Fashion-MNIST, and CIFAR-10. Results show that our methods outperform state-of-the-art supervised STDP learning rules, for comparable architectures and numbers of neurons. Further analysis demonstrates that the use of PCN enhances the performance of S2-STDP, regardless of the hyperparameter set and without introducing any additional hyperparameters.

A novel ensemble causal feature selection approach with mutual information and group fusion strategy for multi-label data

PurposeAs intelligent technology advances, practical applications often involve data with multiple labels. Therefore, multi-label feature selection methods have attracted much attention to extract valuable information. However, current methods tend to lack interpretability when evaluating the relationship between different types of variables without considering the potential causal relationship.Design/methodology/approachTo address the above problems, we propose an ensemble causal feature selection method based on mutual information and group fusion strategy (CMIFS) for multi-label data. First, the causal relationship between labels and features is analyzed by local causal structure learning, respectively, to obtain a causal feature set. Second, we eliminate false positive features from the obtained feature set using mutual information to improve the feature subset reliability. Eventually, we employ a group fusion strategy to fuse the obtained feature subsets from multiple data sub-space to enhance the stability of the results.FindingsExperimental comparisons are performed on six datasets to validate that our proposal can enhance the interpretation and robustness of the model compared with other methods in different metrics. Furthermore, the statistical analyses further validate the effectiveness of our approach.Originality/valueThe present study makes a noteworthy contribution to proposing a causal feature selection approach based on mutual information to obtain an approximate optimal feature subset for multi-label data. Additionally, our proposal adopts the group fusion strategy to guarantee the robustness of the obtained feature subset.

Enhancing local representation learning through global–local integration with functional connectivity for EEG-based emotion recognition

Emotion recognition based on electroencephalogram (EEG) signals is crucial in understanding human affective states. Current research has limitations in extracting local features. The representation capabilities of local features are limited, making it difficult to comprehensively capture emotional information. In this study, a novel approach is proposed to enhance local representation learning through global–local integration with functional connectivity for EEG-based emotion recognition. By leveraging the functional connectivity of brain regions, EEG signals are divided into global embeddings that represent comprehensive brain connectivity patterns throughout the entire process and local embeddings that reflect dynamic interactions within specific brain functional networks at particular moments. Firstly, a convolutional feature extraction branch based on the residual network is designed to extract local features from the global embedding. To further improve the representation ability and accuracy of local features, a multidimensional collaborative attention (MCA) module is introduced. Secondly, the local features and patch embedded local embeddings are integrated into the feature coupling module (FCM), which utilizes hierarchical connections and enhanced cross-attention to couple region-level features, thereby enhancing local representation learning. Experimental results on three public datasets show that compared with other methods, this method improves accuracy by 4.92% on the DEAP, by 1.11% on the SEED, and by 7.76% on the SEED-IV, demonstrating its superior performance in emotion recognition tasks.

Global and Local Interpretable Machine Learning Allow Early Prediction of Unscheduled Hospital Readmission

Global and Local Interpretable Machine Learning Allow Early Prediction of Unscheduled Hospital Readmission

지속가능한 평생교육 공간으로서 에코뮤지엄에 대한 연구

Objectives The purpose of this study is to study the potential of the ecomuseum as a sustainable lifelong education space. In this study, the potential of the ecomuseum as a sustainable lifelong education space was derived through analysis of the meaning and structure of the ecomuseum from a lifelong education perspective. Methods This study was a literature study and collected domestic and international literature focusing on the topics of sustainability, lifelong education, educational space, and ecomuseum. This study analyzed domestic and international literature collected using educational elements and educational system of lifelong education as an analysis framework. Results First, from a lifelong education perspective, the meaning of the ecomuseum appeared as a region-based expansion space, a connection and integration space of the local environment, and a learning space centered on local residents. Second, from a lifelong education perspective, the structure of the ecomuseum appeared as a cultural heritage learning space of various types in the horizontal dimension and as a learning space of various generations in the vertical dimension. Third, the potential of the ecomuseum as a lifelong education space were as a self-directed learning space for knowledge, a reflective learning space for action, and a community learning space for living together. Conclusions As a sustainable lifelong education space, the ecomuseum needs to build an integrated learning space to improve learners’ potential, a systematic learning space for learners’ continuous growth, and a local community-based learning space for learners’ community learning.

The Role of Local Learning Media in Civics Subjects for Class V Elementary School Students

This research aims to examine the role of local learning media in Civics Education (PKn) subjects for fifth grade students in elementary schools. This research uses a qualitative descriptive method with data collection techniques through observation, interviews, questionnaires and documentation. The research subjects consisted of 30 fifth grade students and one Civics teacher. The research results show that the use of local learning media, such as folklore and traditional games, increases learning motivation, understanding of the material, and student participation in the Civics learning process. As many as 85% of students felt more motivated, and 78% of students understood the material more easily when local learning media was used. In addition, students become more active in class discussions and activities. However, there are several obstacles, such as difficulties in developing teaching materials that are in accordance with local wisdom and limited time and resources. To overcome this obstacle, it is recommended that there be training for teachers and the development of adequate resources. Overall, this research confirms the importance of local learning media in improving the quality of Civics learning and provides practical recommendations for its integration in the curriculum.

Neural network learning and Quantum Gravity

The landscape of low-energy effective field theories stemming from string theory is too vast for a systematic exploration. However, the meadows of the string landscape may be fertile ground for the application of machine learning techniques. Employing neural network learning may allow for inferring novel, undiscovered properties that consistent theories in the landscape should possess, or checking conjectural statements about alleged characteristics thereof. The aim of this work is to describe to what extent the string landscape can be explored with neural network-based learning. Our analysis is motivated by recent studies that show that the string landscape is characterized by finiteness properties, emerging from its underlying tame, o-minimal structures. Indeed, employing these results, we illustrate that any low-energy effective theory of string theory is endowed with certain statistical learnability properties. Consequently, several local learning problems therein formulated, including interpolations and multi-class classification problems, can be concretely addressed with machine learning, delivering results with sufficiently high accuracy.

Performance Evaluation of a Decentralized Learning Architecture for PCB Defect Classification

Printed circuit board (PCB) defect detection, which is an important task in industrial factories, receives great attention from both researchers and practitioners. To achieve high detection accuracy, the traditional training method requires data collection from multiple industrial factories. However, in practice, factories possess their own data and do not want to share the private data with other participants. Therefore, we introduce a decentralized learning method that makes use the knowledge of clients in the system. By leveraging the federated learning technique, a consensus global detection model can be produced while maintaining data privacy. We have conducted extensive experiments to evaluate the detection performance under various learning methods: federated learning, centralized learning, and local learning. We also compare the detection performance of two well-known detection models: YOLOv5 and YOLOv8. The experimental results show that the federated learning based method yields better detection performance than the local learning.

Machine learning without a processor: Emergent learning in a nonlinear analog network

Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic contrastive local learning networks (CLLNs) offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here, we introduce a nonlinear CLLN-an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR (exclusive or) and nonlinear regression, without a computer. We find our decentralized system reduces modes of training error in order (mean, slope, curvature), similar to spectral bias in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning.

Robust Audio-Visual Contrastive Learning for Proposal-Based Self-Supervised Sound Source Localization in Videos.

By observing a scene and listening to corresponding audio cues, humans can easily recognize where the sound is. To achieve such cross-modal perception on machines, existing methods take advantage of the maps obtained by interpolation operations to localize the sound source. As semantic object-level localization is more attractive for prospective practical applications, we argue that these map-based methods only offer a coarse-grained and indirect description of the sound source. Additionally, these methods utilize a single audio-visual tuple at a time during self-supervised learning, causing the model to lose the crucial chance to reason about the data distribution of large-scale audio-visual samples. Although the introduction of Audio-Visual Contrastive Learning (AVCL) can effectively alleviate this issue, the contrastive set constructed by randomly sampling is based on the assumption that the audio and visual segments from all other videos are not semantically related. Since the resulting contrastive set contains a large number of faulty negatives, we believe that this assumption is rough. In this paper, we advocate a novel proposal-based solution that directly localizes the semantic object-level sound source, without any manual annotations. The Global Response Map (GRM) is incorporated as an unsupervised spatial constraint to filter those instances corresponding to a large number of sound-unrelated regions. As a result, our proposal-based Sound Source Localization (SSL) can be cast into a simpler Multiple Instance Learning (MIL) problem. To overcome the limitation of random sampling in AVCL, we propose a novel Active Contrastive Set Mining (ACSM) to mine the contrastive sets with informative and diverse negatives for robust AVCL. Our approaches achieve state-of-the-art (SOTA) performance when compared to several baselines on multiple SSL datasets with diverse scenarios.

Reduced-Reference Learning for Target Localization in Deep Brain Stimulation.

This work proposes a supervised machine learning method for target localization in deep brain stimulation (DBS). DBS is a recognized treatment for essential tremor. The effects of DBS significantly depend on the precise implantation of electrodes. Recent research on diffusion tensor imaging shows that the optimal target for essential tremor is related to the dentato-rubro-thalamic tract (DRTT), thus DRTT targeting has become a promising direction. The tractography-based targeting is more accurate than conventional ones, but still too complicated for clinical scenarios, where only structural magnetic resonance imaging (sMRI) data is available. In order to improve efficiency and utility, we consider target localization as a non-linear regression problem in a reduced-reference learning framework, and solve it with convolutional neural networks (CNNs). The proposed method is an efficient two-step framework, and consists of two image-based networks: one for classification and the other for localization. We model the basic workflow as an image retrieval process and define relevant performance metrics. Using DRTT as pseudo groundtruths, we show that individualized tractography-based optimal targets can be inferred from sMRI data with high accuracy. For two datasets of 280×220/272×227 (0.7/0.8 mm slice thickness) sMRI input, our model achieves an average posterior localization error of 2.3/1.2 mm, and a median of 1.7/1.02 mm. The proposed framework is a novel application of reduced-reference learning, and a first attempt to localize DRTT from sMRI. It significantly outperforms existing methods using 3D-CNN, anatomical and DRTT atlas, and may serve as a new baseline for general target localization problems.

Meta-Path Semantic and Global-Local Representation Learning Enhanced Graph Convolutional Model for Disease-Related miRNA Prediction.

Dysregulation of miRNAs is closely related to the progression of various diseases, so identifying disease-related miRNAs is crucial. Most recently proposed methods are based on graph reasoning, while they did not completely exploit the topological structure composed of the higher-order neighbor nodes and the global and local features of miRNA and disease nodes. We proposed a prediction method, MDAP, to learn semantic features of miRNA and disease nodes based on various meta-paths, as well as node features from the entire heterogeneous network perspective, and node pair attributes. Firstly, for both the miRNA and disease nodes, node category-wise meta-paths were constructed to integrate the similarity and association connection relationships. Each target node has its specific neighbor nodes for each meta-path, and the neighbors of longer meta-paths constitute its higher-order neighbor topological structure. Secondly, we constructed a meta-path specific graph convolutional network module to integrate the features of higher-order neighbors and their topology, and then learned the semantic representations of nodes. Thirdly, for the entire miRNA-disease heterogeneous network, a global-aware graph convolutional autoencoder was built to learn the network-view feature representations of nodes. We also designed semantic-level and representation-level attentions to obtain informative semantic features and node representations. Finally, the strategy based on the parallel convolutional-deconvolutional neural networks were designed to enhance the local feature learning for a pair of miRNA and disease nodes. The experiment results showed that MDAP outperformed other state-of-the-art methods, and the ablation experiments demonstrated the effectiveness of MDAP's major innovations. MDAP's ability in discovering potential disease-related miRNAs was further analyzed by the case studies over three diseases.

Joint Projected Fuzzy Neighborhood Preserving C-means Clustering with Local Adaptive Learning

Graph-based dimensionality reduction approaches are extensively applied for preserving the intrinsic structures of high-dimensional data. To capture discriminative information from data clusters that lack a clear manifold structure, previous studies have combined clustering algorithms with local manifold structure preservation. These methods assume that two neighbor data points share the same cluster label. However, the assumption may not hold for Fuzzy C-Means which may assign two nearby data points to different clusters depending on the distance between data points and cluster centroids. This inconsistency degrades the performance in clustering and dimensionality reduction. To tackle this issue, we propose a novel approach for dimensionality reduction, termed joint Projected Fuzzy Neighborhood Preserving C-means Clustering with Local Adaptive Learning (PFNPCM). PFNPCM learns cluster centroids, sparse membership grades, embedded subspaces, and structured graphs simultaneously and extracts both global and local structures of data. Through clustering data that preserves the local neighborhood structure in a low-dimensional space instead of the original one, PFNPCM can effectively capture both global and local information from the inherent manifold structure and cluster structure. The employment of ℓ2,1-norm as the distance metric in the clustering and the preservation of neighborhood structure further ensure the robustness of clustering results against noise or outliers. To achieve the consistency of the captured global and local discriminative information, PFNPCM adopts a novel fuzzy local similarity measure based on the manifold structure, and the manifold assumption thus holds when partitioning unlabeled samples into subgroups. Massive experiments on diverse well-known datasets demonstrate that PFNPCM is superior to some state-of-the-art methods.