Learning Patterns Research Articles

Generative artificial intelligence in the agri-food value chain - overview, potential, and research challenges

ChatGPT uses a so called Large Language Model (LLM) to provide textual output of analyzed data. Those LLMs are one example for Generative Artificial Intelligence (AI), which focuses on creating new content, e.g., text, images, or music, based on learned patterns. Recently, applications in the food industry and agriculture started to apply Generative AI. This mini review provides an overview about applications of Generative AI in the agri-food supply chain and discusses open research challenges, also in combination with digital twins.

Perception of the Academic Lecturer’s Profile: From Research Orientation to Pedagogic Orientation, and Implications for the Digital Learning of Students

Aim. This study aims to examine the effect of lecturers’ teaching orientations, as perceived by students, on students’ digital learning patterns, differentiating between research-oriented and pedagogy-oriented teaching approaches. Methods. A survey method was employed to collect data from undergraduate students regarding their perceptions of their lecturers’ orientations and their own digital learning patterns. Descriptive statistical analysis, Pearson correlation, and mediation models were utilized to analyse the relationships between variables. Results. The findings indicate that when students perceived the lecturer as research-oriented, no significant indirect association mediated by the digital learning experience was found between the lecturer’s profile and both active and passive digital learning patterns. However, the association between the research-oriented lecturer and active digital learning was partially mediated by the student’s reading habits, while the association with passive digital learning was fully mediated by reading habits. For pedagogy-oriented lecturers, both active and passive digital learning patterns were partially mediated by the student’s learning experience, with no significant mediation by reading habits. Conclusion. The study suggests that research-oriented lecturers influence active digital learning through students’ reading habits, while pedagogy-oriented lecturers influence both active and passive digital learning through students’ digital learning experiences. Understanding these dynamics can help educational institutions support lecturers in their professional development and improve student learning outcomes in digital environments.

ChiSCAT: Unsupervised Learning of Recurrent Cellular Micromotion Patterns from a Chaotic Speckle Pattern.

There is considerable evidence that action potentials are accompanied by "intrinsic optical signals", such as a nanometer-scale motion of the cell membrane. Here we present ChiSCAT, a technically simple imaging scheme that detects such signals with interferometric sensitivity. ChiSCAT combines illumination by a chaotic speckle pattern and interferometric scattering microscopy (iSCAT) to sensitively detect motion in any direction. The technique features reflective high-NA illumination, common-path suppression of vibrations, and a large field of view. This approach maximizes sensitivity to motion, but does not produce a visually interpretable image. We show that unsupervised learning based on matched filtering and motif discovery can recover underlying motion patterns and detect action potentials. We demonstrate these claims in an experiment on blebbistatin-paralyzed cardiomyocytes. ChiSCAT opens the door to action potential measurement in scattering tissue, including a living brain.

An optimized BERT fine-tuned model using an artificial bee colony algorithm for automatic essay score prediction

Background The Automatic Essay Score (AES) prediction system is essential in education applications. The AES system uses various textural and grammatical features to investigate the exact score value for AES. The derived features are processed by various linear regressions and classifiers that require the learning pattern to improve the overall score. Issues Moreover, the classifiers face catastrophic forgetting problems, which maximizes computation complexity and reduce prediction accuracy. The forgetting problem can be resolved using the freezing mechanism; however, the mechanism can cause prediction errors. Method Therefore, this research proposes an optimized Bi-directional Encoder Representation from Transformation (BERT) by applying the Artificial Bee Colony algorithm (ABC) and Fine-Tuned Model (ABC-BERT-FTM) to solve the forgetting problem, which leads to higher prediction accuracy. Therefore, the ABC algorithm reduces the forgetting problem by selecting optimized network parameters. Results Two AES datasets, ASAP and ETS, were used to evaluate the performance of the optimized BERT of the AES system, and a high accuracy of up to 98.5% was achieved. Thus, based on the result, we can conclude that optimizing the BERT with a suitable meta-heuristic algorithm, such as the ABC algorithm, can resolve the forgetting problem, eventually increasing the AES system’s prediction accuracy.

Multi-Cultural and Local Wisdom-based Curriculum Development Model in the Independent Campus Learning Program to Improve Graduates' Micro Skills

In the Independent Campus Learning Program [Merdeka Belajar Kampus Merdeka (MBKM)], the 5-1-2 learning pattern is used in the undergraduate program. In implementing this pattern, curriculum coherence is needed between study programs and between institutions. A model for developing a curriculum based on local wisdom and multiculturalism was created to improve the micro-skills of program graduates. A model for developing a curriculum based on local wisdom and multiculturalism was created to improve the micro-skills of program graduates. A model for developing a curriculum based on local wisdom and multiculturalism was created to improve the micro-skills of program graduates. In order to attain the objective, a hierarchical pattern of relationships is employed, beginning with the central construct, primary dimension, and indicator. A structural Equation Model (SEM) is used to analyse the relationship between variables, while an inductive approach is used for exploratory purposes to identify factors. In order to evaluate the dependability of the model, a study was conducted at two different universities in Indonesia: Sultan Ageng Tirtayasa University in Serang, Banten Province, and Galuh Ciamis University in West Java Province. The study involved testing the coherence of the curriculum of various programs at both universities and evaluating the micro-skills of graduates who had participated in the MBKM program. Samples from the 4 study programs implementing MBKM at the two universities were used to test curriculum coherence. Then, to determine the increase in graduates' micro-skills, a sample of 70 students was used. The results of the analysis show that curriculum development has a direct effect on improving graduates' micro-skills. In developing the curriculum, three factors strengthen micro skills improvement: development of knowledge, responsiveness to technological developments, and relevance to needs.

Deep diffusion learning of mutual-reflective structured light patterns for multi-body three-dimensional imaging

Simultaneous structured light imaging of multiple objects has become more demanding and widely in many scenarios involving robot operations in intelligent manufacturing. However, it is challenged by pattern aliasing caused by mutual reflection between high-reflective objects. To this end, we propose to learn clear fringe patterns from aliased mutual-reflective observations by diffusion models for achieving high-fidelity multi-body reconstruction in line with typical phase-shift algorithms. Regarding mutual reflection imaging as a formation of adding significant noise, we build a supervised generative learning framework based on diffusion models and then train a self-attention-based deep network with a U-Net-like skip-connected encoder-decoder architecture. We demonstrate the generalization capability of the trained model in fringe pattern recovery and its performance in phase and three-dimensional (3D) shape reconstruction. Both experimental results show that the proposed method has the expected feasibility and accuracy, heralding a promising solution for addressing the current challenge in various multi-body mutual-reflective 3D reconstruction tasks.

The influence of e-learning on exam performance and the role of achievement goals in shaping learning patterns

Digital learning environments provide opportunities to support learning in higher education. However, it is yet unclear why and how learners use these opportunities. We propose that learners’ achievement goals and their beliefs regarding the instrumentality of e-learning tools to achieve those goals are predictive for learning behavior within digital learning environments. Furthermore, we assume learning behavior characterized by longer overall learning time, more distributed learning, and less learning delay predicts higher exam performance. To test these hypotheses, we analyzed log-file data of 91 university students who had used an intelligent tutoring system as exam preparation in a pre-registered study. Beyond the overall predictive validity of the intelligent tutoring system, we found a negative association between learning delay and exam performance. Achievement goals predicted learning time and time distribution, an association that was partly moderated by perceived instrumentality. This suggests that goals and beliefs are important puzzle pieces for understanding e-learning (behavior).

Transfer learning of species co-occurrence patterns between plant communities

AimThe use of neural networks (NNs) is spreading to all areas of life, and Ecology is no exception. However, the data-hungry nature of NNs can leave out many small, valuable datasets. Here we show how to apply transfer learning to rescue small datasets that can be invaluable in understanding patterns of species co-occurrence. LocationSemiarid plant communities in Spain and México. Time period2016–2022. Major taxa studiedAngiosperms. MethodsBased on a large sample of plant species co-occurrence in vegetation patches in a semi-arid area of eastern Spain, we fit a generative artificial intelligence (AI) model that correctly reproduces which species live with which in these patches. Subsequently, we train the same type of model on two communities for which we only have smaller datasets (another semi-arid community in eastern Spain, and a tropical community in Mexico). ResultsWhen we transfer the knowledge learnt from the large dataset directly to the other two, the predictions improve for the community more similar to our reference one. As for the more dissimilar community, improving the accuracy of the transfer requires a further tuning of the model to the local data. In particular, the knowledge transferred relates primarily to species frequency and, to a lesser extent, to their phylogenetic relationships, which are known to be determinants of species interaction patterns. Main conclusionsThis AI-based approach can be performed for communities similar or not so similar to the reference community, opening the door to systematic transfer learning for accurate predictions on small datasets. Interestingly, this transfer operates by matching unrelated species between the origin and target datasets, implying that arbitrary datasets can then be transferred to, or even combined in order to augment each other, irrespective of the species involved, potentially allowing such models to be applied to a wide range of plant communities in different climates.

Intelligent cardiovascular disease diagnosis using deep learning enhanced neural network with ant colony optimization

To identify patterns in big medical datasets and use Deep Learning and Machine Learning (ML) to reliably diagnose Cardio Vascular Disease (CVD), researchers are currently delving deeply into these fields. Training on large datasets and producing highly accurate validation results is exceedingly difficult. Furthermore, early and precise diagnosis is necessary due to the increased global prevalence of cardiovascular disease (CVD). However, the increasing complexity of healthcare datasets makes it challenging to detect feature connections and produce precise predictions. To address these issues, the Intelligent Cardiovascular Disease Diagnosis based on Ant Colony Optimisation with Enhanced Deep Learning (ICVD-ACOEDL) model was developed. This model employs feature selection (FS) and hyperparameter optimization to diagnose CVD. Applying a min–max scaler, medical data is first consistently prepared. The key feature that sets ICVD-ACOEDL apart is the use of Ant Colony Optimisation (ACO) to select an optimal feature subset, which in turn helps to upgrade the performance of the ensuring deep learning enhanced neural network (DLENN) classifier. The model reforms the hyperparameters of DLENN for CVD classification using Bayesian optimization. Comprehensive evaluations on benchmark medical datasets show that ICVD-ACOEDL exceeds existing techniques, indicating that it could have a significant impact on CVD diagnosis. The model furnishes a workable way to increase CVD classification efficiency and accuracy in real-world medical situations by incorporating ACO for feature selection, min–max scaling for data pre-processing, and Bayesian optimization for hyperparameter tweaking.

Novel Machine Learning of DNA Methylation Patterns to Diagnose Complex Disease: Identification of Cerebral Palsy with Concurrent Epilepsy.

Spastic cerebral palsy (CP) is a common pediatric-onset disability with an estimated prevalence of 0.2%. It is a complex condition characterized by muscle stiffness, contractures, and abnormal movement. Spastic CP is difficult to diagnose. Although nearly all affected children are born with it or acquire it immediately after birth, many are not identified until after 19 months of age with the diagnosis often not confirmed until 5 years of age. In addition, CP frequently co-occurs with other complex conditions that can complicate diagnosis and treatment. For example, an estimated 42% of spastic CP cases have co-occurring epilepsy. Recent studies indicate that altered DNA methylation patterns in peripheral blood cells are associated with CP and may have diagnostic value.Accordingly, the purpose of this study is to assess the diagnostic value of methylation in CP with more complex disease states. We evaluated machine learning classification for detecting CP based on DNA methylation pattern analysis in the context of co-occurrent epilepsy. Blood samples from 30 study participants diagnosed with epilepsy (n=4), spastic CP (n=10), both (n=8), or neither (n=8) were analyzed by Illumina MethylationEpic arrays. A novel machine learning algorithm using a Support Vector Machine (SVM) or Linear Discriminant Analysis (LDA) was developed to identify methylation loci that classified CP from controls and to measure the classification ability of identified methylation loci. The isolation of informative methylation loci was performed in a binary comparison between CP and controls, as well as in a 4-way comparison that included epilepsy. Median F1 scores for SVM-based analysis were 0.67 in 4-class comparison, and 1.0 in the binary classification. SVM outperformed LDA (median F1 0.57 and 0.86, respectively). Overall, the novel machine learning based algorithm was able to classify study participants with spastic CP and/or epilepsy from controls with significant performance.

Multi-Objective Design of DNA-Stabilized Nanoclusters Using Variational Autoencoders With Automatic Feature Extraction.

DNA-stabilized silver nanoclusters (AgN-DNAs) have sequence-tuned compositions and fluorescence colors. High-throughput experiments together with supervised machine learning models have recently enabled design of DNA templates that select for AgN-DNA properties, including near-infrared (NIR) emission that holds promise for deep tissue bioimaging. However, these existing models do not enable simultaneous selection of multiple AgN-DNA properties, and require significant expert input for feature engineering and class definitions. This work presents a model for multiobjective, continuous-property design of AgN-DNAs with automatic feature extraction, based on variational autoencoders (VAEs). This model is generative, i.e., it learns both the forward mapping from DNA sequence to AgN-DNA properties and the inverse mapping from properties to sequence, and is trained on an experimental data set of DNA sequences paired with AgN-DNA fluorescence properties. Experimental testing shows that the model enables effective design of AgN-DNA emission, including bright NIR AgN-DNAs with 4-fold greater abundance compared to training data. In addition, Shapley analysis is employed to discern learned nucleobase patterns that correspond to fluorescence color and brightness. This generative model can be adapted for a range of biomolecular systems with sequence-dependent properties, enabling precise design of emerging biomolecular nanomaterials.

Lung cancer classification model using convolutional neural network with feature ranking process

Abstract Lung cancer is the leading cause of cancer-related deaths worldwide, highlighting the importance of early detection to improve patient outcomes. The goal of this study is to create a computer-aided diagnosis (CAD) system that detects and classifies lung cancer based on medical images using a Convolutional Neural Network (CNN) and feature extraction techniques. The study employs the LIDC-IDRI dataset, a comprehensive collection of lung cancer-related medical images, to achieve this goal. Contrast Limited Adaptive Histogram Equalization (CLAHE) is used to improve contrast and detail while reducing noise. The Sobel operator is used to refine the segmentation process by enhancing edges and contours in binary images. Morphological operations such as dilation and filling are used to refine the segmented regions even further. Feature extraction is used to extract statistical data and texture characteristics from segmented regions. Mean and variance calculations reveal information about brightness and variability within regions, whereas co-occurrence matrices and Gray-Level Co-occurrence Matrix (GLCM) properties quantify texture features. The correlation between different regions is also evaluated to assess their relationships. Using the pre-processed and ranked features as inputs, a CNN model with five hidden layers is trained. To classify the segmented regions into cancerous and non-cancerous classes, the model learns patterns and relationships in the data. A confusion matrix is used to assess the accuracy, specificity, and sensitivity of the model's predictions, with an emphasis on correctly identifying lung cancer-affected regions. The results show promising results, with the proposed CAD system identifying lung cancer-affected regions with an accuracy of 99.4375%. The system also outperforms other existing methods with a specificity of 99.12% and a sensitivity of 99.26%. These findings highlight the developed system's potential as a valuable tool for early lung cancer detection, assisting doctors in making accurate diagnoses and improving patient outcomes.

EXPRESS: Investigating a Metrical Hebb Effect for lists of words.

In four experiments, we describe the first finding of a Metrical Hebb Effect. Participants are shown to exhibit a Hebb Repetition Effect for repeating, list-wide stress patterns across sequences of familiar words, even though the lexical items within the "repeating" lists do not themselves repeat. Experiment 1 established the presence of a Hebb effect for metrical patterns, demonstrating significant learning of list-wide metrical patterns over successive presentations. Experiment 2 investigated the effect's longevity, showing persistence of learned metrical information after a spacing of three non-repeating lists. Experiment 3 revealed that the effect did not persist over a longer spacing, of eight intervening lists. Experiment 4 investigated the learning mechanism, suggesting that chunking, rather than item-position binding, might account for the observed learning of metrical patterns. The authors propose that metrical-pattern learning represents a process of gradual integration of sequences of weak and strong stress accents, into higher-level units representing the stress patterns within, and across, words. We briefly discuss some implications of the Metrical Hebb Effect for phonological word-form learning, and for speech perception and production.

EXPRESS: Language structure reflects biases in pattern learning across domains and modalities.

A central goal for psychological science is the explanation of variation in human behaviour. In the domain of language, patterns of cross-linguistic variation have been extensively documented, but there has been vigorous debate over how to explain them. A particularly contentious question is whether constraints on linguistic variation are driven by properties of the human mind that are specific to language, or domain general. In this paper, we present four pattern-learning experiments (N=306 English- and Italian-speaking adults) across domains (linguistic and non-linguistic) and modalities (visual, auditory, and tactile) to show that the patterns that are more easily learned are precisely the ones that are found most frequently across languages. This supports a domain-general, cognitive explanation for cross-linguistic variation. However, we suggest that the general/specific dichotomy is ultimately misleading because language structure arises when domain- and modality-general biases meet domain-specific representations.

Interpretable neuro-cognitive diagnostic approach incorporating multidimensional features

Cognitive diagnostics is a pivotal area within educational data mining, focusing on deciphering students’ cognitive status via their academic performance. Traditionally, cognitive diagnostic models (CDMs) have evolved from manually designed probabilistic graphical models to sophisticated automated learning models employing neural networks. Despite their enhanced fitting capabilities, contemporary neuro-cognitive diagnostic models frequently overlook critical process information from students and suffer from reduced interpretability. To address these limitations, this paper introduces a neuro-cognitive diagnostic model that integrates multidimensional features (MFNCD) by incorporating students’ response time as process information. This approach facilitates the simultaneous modeling of students’ response accuracy and response speed using neural networks, thereby enhancing both the fitting capability and precision of the method. Furthermore, a multi-channel attention mechanism is employed to effectively capture the complex interactions between students and exercise characteristics, simulating the process of students answering questions and thereby improving the model's interpretability. Validated on four diverse datasets, MFNCD model demonstrates superior accuracy compared to other state-of-the-art (SOAT) baseline models. Additionally, our experiments confirm significant correlations between cognitive attributes, revealing interesting educational patterns, such as a positive correlation between speed and ability, and between ability and accuracy. These findings provide deeper insights into learning patterns that incorporate multidimensional features and suggest potential pathways for targeted educational interventions.

The Hippocampus Represents Information about Movements in Their Temporal Position in a Learned Motor Sequence.

Our repertoire of motor skills is filled with sequential movements that need to be performed in a specific order. Here, we used functional magnetic resonance imaging to investigate whether the human hippocampus, a region known to support temporal order in non-motor memory, represents information about the order of sequential motor actions in human participants (both sexes). We also examined such representations in other regions of the motor network (i.e., the premotor cortex, supplementary motor area, anterior superior parietal lobule, and striatum) already known for their critical role in motor sequence learning. Results showed that the hippocampus represents information about movements in their learned temporal position in the sequence, but not about movements or temporal positions in random movement patterns. Other regions of the motor network coded for movements in their learned temporal position, as well as movements and positions in random movement patterns. Importantly, movement coding contributed to sequence learning patterns in primary, supplementary, and premotor cortices but not in striatal and parietal regions. Our findings deepen our understanding of how striatal and cortical regions contribute to motor sequence learning and point to the capacity of the hippocampus to represent movements in their temporal context, an ability possibly explaining its contribution to motor learning.

Research on flexible antenna and distributed deep learning pattern recognition for partial discharge monitoring of transformer

Research on flexible antenna and distributed deep learning pattern recognition for partial discharge monitoring of transformer

Pola Belajar Mahasiswa Pekerja Part time: Studi di Universitas Islam Negeri Sumatera Utara Jurusan PAI

This research aims to examine the learning patterns of part-time student students studying at the State Islamic University of North Sumatra majoring in PAI. This study used descriptive qualitative method. Data collection techniques were used by means of observation, interviews and documentation. The results of the research show that students who work part time at UINSU majoring in PAI predominantly choose independent study patterns because of the flexibility of time that fits their busy schedules. The second most popular learning pattern is peer tutoring. Meanwhile, only a small number of students choose discussion or group learning patterns. Thus, from the results of this research it can be concluded that part-time working students at the State University of North Sumatra, Department of Islamic Religious Education, predominantly choose independent study patterns.

Applications of deep learning in mathematics education: A review

Traditional classroom settings often fail to account for individual differences, leading to disparities in student performance. Deep learning models offer a solution by analyzing performance data to provide targeted interventions and immediate feedback, thereby personalizing educational experiences. This review examines the transformative potential of deep learning in mathematics education through various applications and methodologies. Studies show that deep learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), can analyze complex student data, identify learning patterns, and offer real-time, personalized support. Notable applications include automated classroom feedback systems, intelligent tutoring systems, and predictive models for student performance. Despite the promising results, challenges such as data quality, computational resources, model interpretability, and potential biases remain. Future research should focus on creating inclusive datasets, improving computational efficiency, and enhancing model transparency to fully harness the benefits of deep learning in educational settings.

Fast clustering and cell-type annotation of scATAC data using pre-trained embeddings.

Data from the single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) are now widely available. One major computational challenge is dealing with high dimensionality and inherent sparsity, which is typically addressed by producing lower dimensional representations of single cells for downstream clustering tasks. Current approaches produce such individual cell embeddings directly through a one-step learning process. Here, we propose an alternative approach by building embedding models pre-trained on reference data. We argue that this provides a more flexible analysis workflow that also has computational performance advantages through transfer learning. We implemented our approach in scEmbed, an unsupervised machine-learning framework that learns low-dimensional embeddings of genomic regulatory regions to represent and analyze scATAC-seq data. scEmbed performs well in terms of clustering ability and has the key advantage of learning patterns of region co-occurrence that can be transferred to other, unseen datasets. Moreover, models pre-trained on reference data can be exploited to build fast and accurate cell-type annotation systems without the need for other data modalities. scEmbed is implemented in Python and it is available to download from GitHub. We also make our pre-trained models available on huggingface for public use. scEmbed is open source and available at https://github.com/databio/geniml. Pre-trained models from this work can be obtained on huggingface: https://huggingface.co/databio.