The success of deep learning (DL) in offline brain-computer interfaces (BCIs) has not yet translated into efficient online applications. This is due to two limiting factors: the need for large amounts of training data in DL and the fact that current DL solutions are primarily developed for offline decoding. To enable real-time decoding, even across subjects without calibration data, we first introduce a novel method real-time adaptive pooling (RAP) to tune existing offline DL models towards online decoding by modifying the pooling layers. To reduce the amount of training data required, our approach leverages different levels of domain adaptation. We show how different settings enable different adaptation solutions. Our results demonstrate that our approach is both powerful and can be calibration-free, providing a robust and practical solution for real-time BCI applications. These findings pave the way for the development of co-adaptive and highly efficient DL-based BCI systems.

In computer vision, human action recognition is a hot topic, popularized by the development of deep learning. Current models have achieved high accuracy results on public datasets. Despite this success, they require significant computational resources for training. Given that transfer learning based techniques allow reusing what other models have already learned and training models with less computational resources, in this work we propose using a transfer learning based approach for action recognition in videos. We describe a methodology for human action recognition using transfer learning techniques in a custom dataset. The proposed method consists of four stages: 1) human detection and tracking, 2) video preprocessing, 3) feature extraction (using pretrained models with ImageNet), and 4) action recognition using a two-stream model consisting of TCNs, LSTMs, and CNNs layers. The custom dataset is imbalanced with 189, 390, 490, 854, and 890 videos per class, respectively. For feature extraction, we analyzed the performance of seven pretrained models: Inception-v3, MobileNet-v2, MobileNet-v3-L, VGG-16, VGG-19, Xception, and ConvNeXt-L. We show that the best results were obtained with the last one. Finally, using pretrained models for feature extraction allowed training in a PC with a single GPU with an accuracy of 94.9%.

Exploring new approaches to innovating higher vocational education is a worldwide pursuit driven by the increasing demand for graduates equipped with competencies. This study investigated how Outcomes-Based Education (OBE) influences the attainment of graduate competence (AGC) in China’s higher vocational education, using the theory of Constructive Alignment (CA) as its foundation. The OBE framework incorporates intended learning outcomes (ILOs), project-based learning (PjBL), assessment strategies (ASs), and AGC. The study tested the model by assessing the impact of ILOs, PjBL, and ASs on AGC, respectively and sequentially. Surveys were administered to 320 CBEC learners in April 2024, resulting in 301 usable responses. Data were analyzed using structural equation modeling (SEM) with SPSS 23.0 and AMOS 24.0. Results indicated that PjBL and ASs were directly and positively related to graduate competency attainment, while ILOs were indirectly associated with graduate competence through the mediating roles of PjBL and ASs. The most substantial mediating effect between ILOs and graduate competence was ASs, followed by PjBL, and then, the chain mediating effect of PjBL and ASs. These findings enhance the theoretical understanding of OBE and provide detailed procedures for tracking and enhancing sustainability in higher vocational education. Beneficiaries include educators, policymakers, and accreditation bodies.

Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully-supervised, requiring extensive precise manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains challenging to train large-scale segmentation models when confronted with limited colonoscopy data. To address these issues, we introduce the general segmentation foundation model—Segment Anything Model (SAM) into the field of medical image segmentation. Fine-tuning the foundation model is an effective approach to tackle sample scarcity. However, current SAM fine-tuning techniques still rely on precise annotations. To overcome this limitation, we propose WSPoly-SAM, a novel weakly-supervised approach for colonoscopy polyp segmentation. WSPoly-SAM utilizes weak annotations to guide SAM in generating segmentation masks, which are then treated as pseudo-labels to guide the fine-tuning of SAM, thereby reducing the dependence on precise annotations data. To improve the reliability and accuracy of pseudo-labels, we have designed a series of enhancement strategies to improve the quality of pseudo-labels and mitigate the negative impact of low-quality pseudo-labels. Experimental results on five medical image datasets demonstrate that WSPoly-SAM outperforms current fully-supervised mainstream polyp segmentation networks on the Kvasir-SEG, ColonDB, CVC-300, and ETIS datasets. Furthermore, by using different amounts of training data in weakly-supervised and fully-supervised experiments, it is found that weakly-supervised fine-tuning can save 70% to 73% of annotation time costs compared to fully-supervised fine-tuning. This study provides a new perspective on the combination of weakly-supervised learning and SAM models, significantly reducing annotation time and offering insights for further development in the field of colonoscopy polyp segmentation.

1) Background: Several studies have shown the benefit of drawing when learning anatomy. Virtual Reality (VR) also appears to be useful to increase the understanding of the location of anatomical structures. This study aims to describe how students in an Operating Room Nursing (OR nursing) master study program perceive the benefit of active learning methods, including drawing and the use of VR. 2) Methods: We combined these two methods in a class of 29 students. 38 half-finished drawings of anatomical structures were made. The students were to complete these during lectures with guidance from the teacher. The students also attended a two-hour VR session where they were to find various anatomical structures. A paper questionnaire was applied to evaluate the teaching program. Data were analyzed statistically. 3) Results: The students highly appreciated these learning methods. They reported that drawing made them work more actively during lectures and increased their learning outcome. They also perceived that the use of VR technology increased their understanding of the location of anatomical structures. 4) Conclusion: The combination of drawing and VR technology may be of benefit to OR Nursing students when learning anatomy by both increasing student activity and learning outcomes.

This paper presents a novel framework for Collaborative Learning Networks (CLNs) in classrooms, aiming to optimize resource utilization and enhance educational services. The study addresses the inefficiencies of traditional education models, particularly the underutilization of computational resources and limited access to specialized software. The proposed framework employs a mix of task-based and random allocation strategies to distribute computational tasks within the CLN, considering each device’s capabilities and task requirements. The findings show significant improvement in resource utilization, facilitated by device-to-device collaboration and task sharing, thus enriching students’ learning experiences. This work contributes to optimizing resource utilization in education, advancing the field of CLNs.

The use of video in education has become ubiquitous as technological developments have markedly improved the ability and facility to create, deliver and view videos. The concomitant pedagogical transformation has created a sense of urgency regarding how video may be used to advance learning. Initial reviews have suggested only limited potential for the use of video in higher education. More recently, a systematic review of studies on the effect of video use on learning in higher education, published in the prestigious Review of Educational Research, found, overall, effects to be positive. In the present paper we critique this study and provide some needed clarity to the state of research on learning via video in higher education. We reveal significant gaps in the study methodology and write-up and use a cognitive processing lens to critically assess and reanalyse study data. We found results of this study to be only applicable to learning requiring lower-level cognitive processing and conclude, consistent with prior research, learning benefits remain limited.

Intelligent Tutoring Systems (ITS) are increasingly popular for online learning. These systems use adaptive algorithms to recommend relevant content based on students' profiles. However, instructors need to periodically assess students' performance to ensure learning outcomes and adjust strategies accordingly. Our objective is to predict students' progress in advance, enabling teachers to make quicker decisions and facilitating the iterative process of adaptive algorithms. For this study, we collected a dataset from ALIN, an online learning platform, consisting of over 5,000 students' learning records and test results. Using this dataset, we conducted experiments employing various machine learning algorithms. The results indicate that learning behavior contributes to improving forecast performance, while students' progress strongly correlates with their previous test results. Additionally, we discovered that students' progress can be indirectly predicted by forecasting their scores. Furthermore, by breaking down overall scores into several distinct components and predicting individual scores for each component, the accuracy of the forecasts can be improved.

This paper investigates the adaptability of four state-of-the-art Artificial Intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n=856 cancer cases and n=856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish image subsets. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&H and End2End AI models, both in the pre-trained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by GLAM model (0.909), I&H (0.893) and End2End (0.875). There were significant differences (P<0.05) in the performances of the four AI models between high-concordance subset and entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with strong concordance of radiologists’ annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models.

Equipping autonomous agents for dynamic interaction and navigation is a significant challenge in intelligent transportation systems. This study aims to address this by implementing a brain-inspired model for decision-making in autonomous vehicles. We employ active inference, a Bayesian approach that models decision-making processes similar to the human brain, focusing on the agent's preferences and the principle of free energy. This approach is combined with imitation learning to enhance the vehicle's ability to adapt to new observations and make human-like decisions. The research involved developing a multi-modal self-awareness architecture for autonomous driving systems and testing this model in driving scenarios, including abnormal observations. The results demonstrated the model's effectiveness in enabling the vehicle to make safe decisions, particularly in unobserved or dynamic environments. The study concludes that the integration of active inference with imitation learning significantly improves the performance of autonomous vehicles, offering a promising direction for future developments in intelligent transportation systems.

Data mining techniques have garnered significant attention within the realm of education. However, the procurement of ample student data poses a formidable challenge. In response to this challenge, we present a student dataset characterized by its size and distinctive attributes. This dataset encompasses various task-related topics interconnected through a learning pathway, thereby enabling researchers to delve into the data from novel perspectives. Moreover, it encompasses extensive longitudinal student behavioral data, a rarity that adds substantial value. Spanning the years from 2010 to 2021, our dataset comprises a cohort of 7,933 students, 64,344 test scores, and 183,390 behavior records, solidifying its status as a valuable resource for educational research. In our experiments, we achieved successful predictions of students' test outcomes based on behavioral learning data. The strengths of our dataset render it apt for analyzing the nexus between student conduct and academic performance, crafting personalized learning recommendations, and pursuing various other research pursuits.

In the realm of mathematics education, self-explanation stands as a crucial learning mechanism, allowing learners to articulate their comprehension of intricate mathematical concepts and strategies. As digital learning platforms grow in prominence, there are mounting opportunities to collect and utilize mathematical self-explanations. However, these opportunities are met with challenges in automated evaluation. Automatic scoring of mathematical self-explanations is crucial for preprocessing tasks, including the categorization of learner responses, identification of common misconceptions, and the creation of tailored feedback and model solutions. Nevertheless, this task is hindered by the dearth of ample sample sets. Our research introduces a semi-supervised technique using the Language Learning Model (LLM), specifically its Japanese variant, to enrich datasets for the automated scoring of mathematical self-explanations. We rigorously evaluated the quality of self-explanations across five datasets, ranging from human-evaluated originals to ones devoid of original content. Our results show that combining LLM-based explanations with mathematical material significantly improves the model's accuracy. Interestingly, there's an optimal limit to how much synthetic self-explanation data can bene-fit the system. Exceeding this limit doesn't further improve outcomes. This study thus highlights the need for careful consideration when integrating synthetic data into solutions, especially within the mathematics discipline.

The zero-catch problem is a key issue in CPUE(Catch Per Unit Effort) standardization, and previous studies have treated all zero-catch data uniformly, but this actually loses some correctly-labeled samples. On the other hand, for the main catches with few zero-catch samples, the problem of low performance of fisheries forecasting remains unsolved even though the forecasting model structure is updating constantly, since we cannot know whether the samples are correctly recorded. In this paper, we propose a method based on confident learning theory to detect anomalous samples in the datasets and unify zero-catch and non-zero samples as noise through an overarching framework of learning with noisy labels, which reveals the heterogeneity among zero-catch samples (as well as among non-zero samples) and the homogeneity between zero-catch samples and non-zero samples. Using three species of tuna in the tropical Atlantic Ocean with the spatial resolution of 0.5 ◦ × 0.5 ◦ and time resolution of days from 2016 to 2019 as experimental material, performance on all three classical machine learning models(Random forest, Support Vector Machine and XGBoost) is significantly improved compared to each baseline.This confirms that we propose a self-adaptive, effective method for detecting and repairing anomalous samples in the fishery dataset.

This study explores the Edaravone solubility space encompassing both neat and binary dissolution media. The efforts were made toward revealing the concentration limits inherently associated with common pure and mixed solvents. For this purpose, the published solubility data of the title drug were scrupulously inspected and cured. This enabled to make the dataset consistent and coherent. However, the lack of some important types of solvents in the collection called for an extension of the available pool of Edaravone solubility data. Hence, new measurements were performed for collecting Edaravone solubility in polar non-protic and polar di-protic media. Such an extended set of data was used for tuning the parameters of regressors models and formulating the ensemble for predicting new data. In both phases, namely the model training and ensemble formulation, close attention was paid not only to minimizing the deviation of computed values from the experimental ones but also to ensuring the high predictive power and computing solubility for new systems. Furthermore, the environmental friendliness characteristics determined based on the common green solvent selection criteria was included in the analysis. Our applied protocol led to the conclusion that the solubility space defined by ordinary solvents is limited, and it is unlikely to find solvents that are more suited for Edaravone dissolution than those depicted in this manuscript. The theoretical framework presented in this study provides a precise guide for conducting experiments, saving time and resources in the pursuit of new findings.

The use of artificial intelligence (AI) applications in education has the potential to revolutionize the learning experience for international students, who face unique challenges when studying in a foreign country. This paper explores various examples of AI applications in education and their potential impact on international students. AI applications such as personalized learning experiences, adaptive testing, predictive analytics, and chatbots for learning and research are examined for their potential to improve learning efficiency and provide customized education support. It also explores the significant risks and limitations associated with AI technologies, such as privacy, cultural differences, language proficiency, and ethical implications. To maximize the potential benefits of AI applications in higher education, it is crucial to implement appropriate safeguards and regulations. This paper provides a starting point for research on the potential impact of artificial intelligence on international students’ educational experiences and how AI may be integrated into educational administration and learning processes.

Transcutaneous injection laryngoplasty is a well-known procedure for treating paralyzed vocal fold by injecting augmentation material into it. Hence, vocal fold localization plays a vital role in the preoperative planning as the fold location is required to determine the optimal injection route. In this communication, we propose a mirror environment based reinforcement learning (RL) algorithm for localizing the right and left vocal folds in preoperative neck CT. RL-based methods commonly showed noteworthy outcome in general anatomic landmark localization problem in the recent years. However, such methods suggest training individual agent for localizing each fold, though the right and left vocal folds are located in close proximity and have high feature-similarity. Utilizing the lateral symmetry between the right and left vocal folds, the proposed mirror environment allows for a single agent for localizing both the folds by treating the left fold as a flipped version of the right fold. Thus, localization of both folds can be trained using a single training session which utilizes the inter-fold correlation and avoids redundant feature learning. Experiment with 120 CT volumes showed improved localization performance and training efficiency of the proposed method compared with the standard RL method.

Data sets for medical images are generally imbalanced and limited in sample size because of high data collection costs, time-consuming annotations, and patient privacy concerns. The training of deep neural network classification models on these data sets to improve the generalization ability does not produce the desired results for classifying the medical condition accurately and often overfit the data on the majority of class samples. To address the issue, we propose a framework for improving the classification performance metrics of deep neural network classification models using transfer learning: pre-trained models, such as Xception, InceptionResNet, DenseNet along with the Generative Adversarial Network (GAN) – based data augmentation. Then, we trained the network by combining traditional data augmentation techniques, such as randomly flipping the image left to right and GAN-based data augmentation, and then fine-tuned the hyper-parameters of the transfer learning models, such as the learning rate, batch size, and the number of epochs. With these configurations, the Xception model outperformed all other pre-trained models achieving a test accuracy of 98.7%, the precision of 99%, recall of 99.3%, f1-score of 99.1%, receiver operating characteristic (ROC) - area under the curve (AUC) of 98.2%.

Ethnopharmacology experts face several challenges when identifying and retrieving documents and resources related to their scientific focus. The volume of sources that need to be monitored, the variety of formats utilized, the different quality of language use across sources, present some of what we call “big data” challenges in the analysis of this data. This study aims to understand if and how experts can be supported effectively through intelligent tools in the task of ethnopharmacological literature research. To this end, we utilize a real case study of ethnopharmacology research, aimed at the Southern Balkans and Coastal zone of Asia Minor. Thus, we propose a methodology for more efficient research in ethnopharmacology. Our work follows an “Expert-Apprentice” paradigm in an automatic URL extraction process, through crawling, where the apprentice is a Machine Learning (ML) algorithm, utilizing a combination of Active Learning (AL) and Reinforcement Learning (RL), and the Expert is the human researcher. ML-powered research improved 3.1 times the effectiveness and 5.14 times the efficiency of the domain expert, fetching a total number of 420 relevant ethnopharmacological documents in only 7 hours versus an estimated 36-hour human-expert effort. Therefore, utilizing Artificial Intelligence (AI) tools to support the researcher can boost the efficiency and effectiveness of the identification and retrieval of appropriate documents.

The study is an attempt to enquire into the preference of undergraduate students, after a considerable and over a year-long experience with Online Teaching and Learning (OTL), under the emergency preventive measure of switching from the traditional face-to-face classes to online. The study followed an exploratory approach, with a quantitative survey followed by a qualitative one, and a convenient sampling method to collect responses from a substantial sample size. The study is positioned after more than a year of remote classes by the undergraduate student, and hence represents highly experienced reflections and preferences from these students, as compared to other studies conducted last year. The study has profound implications in considering, and questioning, the importance of on-campus classes, and significance of the physical presence of a tutor in the class, and its effect on the learning experience of undergraduate students.

Anomaly occurrences in hydraulic machinery may lead to massive systems shut down, jeopardizing the safety of the machinery and its surrounding human operator(s) and environment, and the severe economic implications succeeding the faults and their associated damage. Hydraulics are mostly placed in ruthless environments, where they are consistently vulnerable to many faults. Hence, not only the machines and their components are prone to anomalies, but also the sensors attached to them, which monitor and report their health and behavioral changes. In this work, a comprehensive applicational analysis of anomalies in hydraulic systems extracted from a hydraulic test rig is thoroughly achieved. Firstly, we provided a combination of a new architecture of LSTM autoencoders and supervised machine and deep learning methodologies to perform two separate stages of fault detection and diagnosis. The two phases are condensed by: the detection phase using the LSTM autoencoder. Followed by the fault diagnosis phase represented by the classification schema. The previously mentioned framework is applied to both component and sensor faults in hydraulic systems, deployed in the form of two in-depth applicational experiments. Moreover, a thorough literature review of the past decade related work for the two stages separately is successfully conducted in this paper.

Radio Frequency Interference (RFI) detection and characterization play a critical role to in ensuring the security of all wireless communication networks. Advances in Machine Learning (ML) have led to the deployment of many robust techniques dealing with various types of RFI. To sidestep an unavoidable complicated feature extraction step in ML, this paper proposes an efficient end-to-end method using the latest advances in deep learning to extract the appropriate features of the RFI signal. Moreover, this study utilizes the benefits of transfer learning to determine both the type of received RFI signals and their modulation types. To this end, the scalogram of the received signals is used as the input of the pre-trained convolutional neural networks (CNN), followed by a fully-connected classifier. This study considers a digital video stream as the signal of interest (SoI), transmitted in a real-time satellite-to-ground communication using DVB-S2 standards. To create the RFI dataset, the SoI is combined with three well-known jammers namely, continuous-wave interference (CWI), multi- continuous-wave interference (MCWI), and chirp interference (CI). This study investigated four well-known pre-trained CNN architectures, namely, AlexNet, VGG-16, GoogleNet, and ResNet-18, for the feature extraction to recognize the visual RFI patterns directly from pixel images with minimal preprocessing. Moreover, the robustness of the proposed classifiers is evaluated by the data generated at different signal to noise ratios (SNR).

This study is a synthesis of 159 articles that were selected for their relevance to comprehend key aspects of the Massive Open Online Courses (MOOCs) phenomenon, from a discourse analysis perspective. Since 2011, MOOCs are expanding worldwide so that the number of subscribers outpointed 101 million at the end of 2018. This paper explores the question whether the MOOCs are the embodiment of the global one-world classroom or whether, instead, they represent a low-cost alternative tailored to a segment that doesn´t have enough time or resources to attend a brick-and-mortar college. In addition, the review tackles the link between motivation and low completion rates. Finally, we discuss the need to devise better methods to assess the pedagogical value of MOOCs.

This paper presents a brief account and rationale for implementation of competency-based learning in any form of management and leadership development programmes in South Africa. The fact that competency-based learning (CBL), also known as outcomes-based learning has been scrapped from the schooling system in South Africa is unfortunate as this method enhances critical thinking skills and practical problem-solving skills. This paper presents CBL as a model of meta-cognitive approach to learning that integrates both theory and practice into experiential learning through six dimensions, namely, active learning, constructive learning, cumulative learning, goal-oriented learning, learner-centred and curriculum design strategies. In the advent of the fast-paced global economy, managers and leaders need to seek those business schools that value real-time practical approach to curriculum for relevance and to maximize shareholder value through human resource development. This brief presentation ends by recommending an approach through CBL that fosters three critical pillars of leadership development, namely: intellectual, behavioural and emotional agenda.

The paper interprets a comparison of two mostly used techniques of a field-oriented control for 6-phase electric drives, with their pros and cons, as well as their differences in construction and behaviour. Both of these approaches have been realized. Frequency and step responses analysis have been demonstrated with a 6-phase permanent magnet synchronous machine. Experimental results have been compared with simulations based on a mathematical model.

The dynamic behaviour of a machine tool (MT) directly influences the machining performances. The adoption of lightweight structures may reduce the effects of undesired vibrations and increasing the workpiece quality. This paper aims to present and compare a set of hybrid materials that may be excellent candidate to fabricate the MT moving parts. The selected materials have high dynamic characteristics and capacity to damp mechanical vibrations. In this way, starting by the kinematic model of a milling machine that highlights the main critical factors, this study paper evaluates a number of prototypes made of Al Foam sandwiches (AFS), Al Corrugated sandwiches (ACS) and materials reinforced by carbon fibres (CFRP). A set of prototypes has been fabricated, represented the Z-axis ram of a commercial milling machine. The static and dynamical properties have been evaluated by using both FE simulations and experimental tests. The obtained results show that the proposed structures may be a valid alternative to the conventional materials of MT moving parts, increasing machining performances. In particular, the AFS prototype highlighted a damping coefficient that is 20 times greater than a conventional ram (e.g. steel). The CFRP structure is able to satisfy the machining requirements with a reduced weight of 48.5%, while the ACS prototype showed a good trade-off between stiffness and damping.

Experiential learning, defined as the result, source, or context of knowledge obtained from direct experience, is increasingly bolstered by technology and human-computer interaction (HCI) principles and protocols. This article will describe how technology-based human-computer interaction (HCI) has been used in experiments to enhance direct knowledge experience. In this paper, immersive technologies (such as Virtual Reality, Augmented Reality, and haptics) will be described based on cognitive learning theory, empirical research and practical experience gained from implementing cutting-edge technology and maximizing HCI principles in constructive learning. Additionally, this article will describe how AI can be used to create individualized learning environments according to a student's needs in the future. While cost, technical issues and specialised trainings are the obstacle to deliver personalized learning experiences especially to economically disadvantaged students, technological change opportunities are projected, and these technologies will take educational outcomes to the next level.

In recent years, the abundance of streaming data has posed significant challenges for traditional machine learning algorithms due to the dynamic nature and high volume of data. To address these challenges, this paper presents an adaptive supervised learning framework designed for data streams, leveraging the power of reproducing kernel Hilbert spaces (RKHS) while incorporating a data sparsity constraint. The proposed framework aims to adaptively update the model to efficiently handle the continuous arrival of streaming data while ensuring accurate and reliable predictions. The primary objective is to exploit the RKHS framework, which provides a rich mathematical structure for learning in high-dimensional feature spaces. By utilizing RKHS, the model can capture complex patterns and nonlinear relationships in the streaming data. Furthermore, the framework incorporates a data sparsity constraint to address the issue of limited resources and computational efficiency. The constraint promotes the selection of a subset of relevant features, reducing the dimensionality of the problem and enhancing the scalability of the learning algorithm. This constraint not only improves computational efficiency but also mitigates the effects of noisy or irrelevant features, leading to more robust and accurate predictions. To achieve adaptability, the proposed framework employs an online learning approach that incrementally updates the model parameters as new data arrives. This allows the model to adapt to concept drift and changing data distributions, ensuring its relevance and effectiveness over time. The adaptation process is guided by a mechanism that balances the exploitation of current knowledge with the exploration of new information, enabling the model to gradually evolve and refine its predictions. Experimental evaluations on various benchmark datasets demonstrate the efficacy of the proposed framework in handling streaming data. The results indicate that the adaptive supervised learning approach in RKHS with a data sparsity constraint outperforms traditional batch learning methods and exhibits superior accuracy, scalability, and adaptability in dynamic data stream scenarios. Overall, this research contributes to the development of adaptive supervised learning methods for data streams, highlighting the effectiveness of RKHS and the significance of incorporating a data sparsity constraint. The proposed framework offers a promising solution to handle the challenges posed by streaming data, paving the way for real-time, efficient, and accurate learning in diverse application domains.

This paper presents an Application Based Active Learning (ABAL) methodology on Power Electronics (PE) and Electric Machines (EM) as a hybrid laboratory course for the undergraduate students to design and implement the real-world engineering problems. The ABAL is a type of active learning which is a branch of Learner-centered teaching (LCT). The DC/DC converter along with the speed control of DC separately excites the motor. In addition, a DC/AC converter is designed to control the speed of an induction motor. The results are then investigated on a hardware platform under the ABAL experimental methodology. This paper also discusses the problem identification selection of the equipment, circuit design, hardware mounting and critical analysis of the results acquired from the hybrid laboratory. The ABAL methodology was evaluated based on student satisfaction, feedback, grades and interest to solve the real-world problem rather than cramming the engineering concepts and fulfill so-called lab routine and tasks

In the domain of financial trading, where accuracy and swift response to data discrep- ancies are paramount for maintaining clienttrust, our research paper delves into the development of a real-time alert system utilizing SpringBoot, a framework renowned for its robustness and adaptability in enterprise applications. We embark on a comprehensive journey, beginning with addressing thefoundational challenges inherent in monitoring trade inquiries - the necessity for real-time processing, unwavering data accuracy,and ensuring unwavering system reliability. The study then methodically transitions to the architectural design, where we explore howSpringBoot’s capabilities are optimally utilized to meet these challenges. Following this, we delve into the im- -plementationphase, detailing the strategic selection of compatible technologies and methods for effective data management and discrepancydetection. The paper culminates in a thorough evalu- ation of the system, where we assess performance across various operationalscenarios, scrutinize the accuracy of the discrepancy detection mechanisms, and integrate real-world feedback from users in thetrading sector. This holistic approach not only highlights the versatility and efficiency of SpringBoot in creating reliable alert systems in the high-stakes world of financial trading but also serves as a detailed guide for similar endeavors in this field

The potential influence of Artificial Intelligence (AI) is obvious in all the elements of teaching and learning processes. Some of the most used methodological approaches of the last decade have been Flipped Classroom and Flipped Learning. This article explores the intersection between Flipped Learning and AI through qualitative research based on interviews with international experts in the field. The results reveal the significant impact of AI on education, highlighting how AI tools are transforming teaching and learning methodologies. Additionally, the evolution of Flipped Learning with the integration of AI is analyzed, showing how this combination enhances personalized learning and improves student engagement. Finally, the role of the teacher in this new educational paradigm is discussed, emphasizing the need for continuous adaptation and the development of new competencies to fully leverage emerging technologies. With this study, we aim to provide an overview of the opportunities and challenges that AI presents in the context of Flipped Learning.

The extensive utilization of drones has led to numerous scenarios that encompass both advantageous and perilous outcomes. By using deep learning techniques, it is aimed to reduce the dangerous effects of drone use through early detection of drones.The state of the art of the study is evaluation of deep learning approaches such as pre trained YOLOv8 drone detection for security issues. In this study, dataset collected by Mehdi Özel for a UAV competition are sourced from GitHub. These images are labeled using Roboflow, and the model is trained on Google Colab. To enhance model performance, dataset augmentation techniques including rotation and blurring are implemented. Following these steps, a significant precision value of 0.946, a notable recall value of 0.9605 and a considerable precision-recall curve value of 0.978 are achieved, surpassing many popular models such as Mask CNN, CNN, and YOLOv5.

This paper highlights the importance of one-shot learning from prototype SKU images for efficient product recognition in retail and inventory management. Traditional methods require large supervised datasets to train deep neural networks, which can be costly and impractical. One-shot learning techniques mitigate this issue by enabling classification from a single prototype image per product class, thus reducing data annotation efforts. We introduce the variational prototyping-encoder (VPE), a novel deep neural network for one-shot classification. Utilizing a support set of prototype SKU images, VPE learns to classify query images by capturing image similarity and prototypical concepts. Unlike metric learning-based approaches, VPE pre-learns image translation from real-world object images to prototype images as a meta-task, facilitating efficient one-shot classification with minimal supervision. Our research demonstrates that VPE can significantly reduce the need for large datasets while accurately classifying query images into their respective categories, providing a practical solution for product classification tasks.

This work discusses the feasibility of multiple linear regression in predicting water/CO₂ relative permeability using training and testing datasets from two nearby wells, separately, of the Lower Cretaceous Lakota Sandstone, Jurassic Hulett Sandstone, and Pennsylvanian Minnelusa Formation at the Dry Fork Station site. The outcome is promising as the predicted and measured relative permeability data are decently comparable. Yet, whether this approach could be generally applicable needs more delicate models and larger training datasets to be determined.

This study explores innovative strategies to enhance hands-on learning experiences in a Database Management Systems (DBMS) course while addressing challenges related to software installation complexities and financial barriers. The investigation focuses on an online course format catering to students majoring in information systems, healthcare administration, business administration, and marketing. Traditional software installation hurdles, especially for complex systems like Microsoft Access and MySQL, can impede students' engagement and access. To overcome these challenges, the study proposes leveraging cloud-based solutions and clientless remote desktop gateways like Apache Guacamole. Results indicate that these approaches effectively eliminate software installation obstacles, ensuring seamless access to essential tools for all students. The study underscores the importance of innovative technological solutions in promoting inclusive and impactful learning environments in higher education.

The importance of sleep for healthy brain function is widely acknowledged. However, it remains unclear how the internal generation of dreams might facilitate cognitive processes. In this perspective we review a computational approach inspired by artificial intelligence that proposes a framework for how dreams occurring during rapid-eye-movement (REM) sleep can contribute to learning and creativity. In this framework, REM dreams are characterized by an adversarial process that, against the dream reality, tell a discriminator network to classify the internally created sensory activity as real. Such an adversarial dreaming process is shown to facilitate the emergence of real-world semantic representations in higher cortical areas. We further discuss the potential contributions of adversarial dreaming beyond learning, such as balancing fantastic and realistic dream elements, and facilitating the occurrence of creative insights. We characterize non-REM (NREM) dreams, where a single hippocampal memory is replayed at a time, as serving a complementary role of improving the robustness of cortical representations to environmental perturbations. We finally explain how subjects can become aware of the adversarial REM dreams, but less of the NREM dreams, and how the awareness phenomenon of wake, dream and lucid dreaming may appear.

The study aimed to investigate the impact of incorporating deep learning strategies in mathematics instruction on students' problem-solving abilities, critical thinking skills, academic achievement, and mathematical skills development. The study population consisted of 280 students, with a sample size of 162 participants. Employing a purely quantitative approach, data collection utilized questionnaires and achievement tests as instruments. Data analysis involved simple linear regression, descriptive analysis, and Pearson correlation. The results of the study revealed that there was no significant enhancement observed in students' problem-solving abilities and critical thinking skills when deep learning strategies were incorporated into mathematics instruction. Additionally, students' attitudes towards deep learning activities in mathematics showed no effect on their academic achievement. Furthermore, students' engagement levels in deep learning activities did not impact their development of mathematical skills. Lastly, the frequency of deep learning activities in the mathematics classroom did not show a significant relationship with students' academic performance. These findings suggest that the implementation of deep learning strategies in mathematics instruction did not yield notable improvements in the specified areas based on the study outcomes.

This study examined how practice distribution schedules influenced accuracy and efficacy in the tennis serve. 24 recreational players were randomized into two experimental groups. Both groups carried out 4 series of 10 services per session during 12 sessions. Massed practice group did not rested between services and rested 10 seconds between series. Distributed practice group rested 10 seconds between services and 30 seconds between series. The accuracy and efficacy were registered and computed based on the 2D digitalization. The learning and retention were tested in a post-test and retention test. The learning program increased the efficacy in the post-test in both groups (p =.001 massed group; p =.015 distributed group). On the retest, the group of massed practice decreased efficacy (p =.021). In accuracy, the group of massed practice reduced its performance in the post-test (p =.015). The effects of the program on the accuracy in the retention test were not observed. It is concluded that this type of sports learning programs, applied at a recreational level, can provide a rigorous approach that contributes with guarantees to the learning of tennis.

The art of representing source code is pivotal in numerous programming analysis applications. Recent strides in neural networks have marked notable successes in this realm. However, the peculiar structural characteristics inherent in programming languages have not been fully exploited in existing models. While neural models based on abstract syntax trees (ASTs) adeptly manage the tree-like nature of source codes, they fall short in discerning the diverse substructural nuances within programs. This paper introduces the Dynamic Syntax Tree Model (DSTM), an innovative approach that fuses various neural network modules into tree architectures tailored to the specific AST of the input. Distinct from preceding tree-based neural models, DSTM adeptly discerns the semantic variances across different AST substructures. We validate DSTM through rigorous testing in program classification and code clone detection, outperforming contemporary methods and demonstrating the benefits of harnessing intricate source code structures.

To identify objects in images, a complex set of skills is needed that includes understanding the context and being able to determine the borders of objects. In computer vision, this task is known as semantic segmentation and it involves categorizing each pixel in an image. It is crucial in many real-world situations: for autonomous vehicles, it enables the identification of objects in the surrounding area; in medical diagnosis, it enhances the ability to detect dangerous pathologies early, thereby reducing the risk of serious consequences. In this study, we compare the performance of various ensembles of convolutional and transformer neural networks. Ensembles can be created, e.g, by varying the loss function, data augmentation method or the learning rate strategy. Our proposed ensemble, which is based on the simple average rule, demonstrates exceptional performance on several datasets. All the resources used in this study are available online at the following GitHub repository: https://github.com/LorisNanni.

Polar Mesospheric Summer Echoes (PMSEs) are radar echoes that are observed in the mesosphere during the Arctic summer months in the polar regions. By studying PMSE, researchers can gain insights into physical and chemical processes that occur in the upper atmosphere specifically in the 80 to 90 km altitude range. In this paper, we employ fully convolutional networks such as UNET and UNET++ for the purposes of segmenting PMSE from the EISCAT VHF dataset. First, experiments are performed to find suitable weights and hyperparameters for UNET and UNET++. Second, different loss functions are tested to find one suitable for our task. Third, as the number of PMSE samples used is relatively small that can lead to poor generalization. To address this, image-level and object-level augmentation methods are employed. Four, we briefly explain our findings by employing layerwise relevance propagation.

In the field of low power wireless networks, one of the techniques on which many researchers are putting their efforts is related to positioning methodologies such as fingerprinting in dense urban areas. This paper presents an experimental study aimed at quantifying the mean location estimation error in densely urbanized areas.Using a dataset made available by the University of Antwerp, a neural network was implemented with the aim of providing the position of the end-devices. In this way it was possible to measure the mean location estimation error in an area with high urban density. The results obtained show an accuracy in the localization of the end-device of less than 150 meters.This result would make it possible to use the fingerprint instead of alternative, energy consuming, methodologies such as GPS in IoT (Internet of Things) applications where battery life is the primary requirement to be met.

Deep learning, specifically the supervised approach, has proved to be a breakthrough in depth prediction. However, the generalization ability of deep networks is still limited, and they cannot maintain a satisfactory performance on some inputs. Addressing a similar problem in the segmentation field, a scheme (f-BRS) has been proposed to refine predictions in the inference time. f-BRS adapts an intermediate activation function to each input by using user clicks as sparse labels. Given the similarity between user clicks and sparse depth maps, this paper aims at extending the application of f-BRS to depth prediction. Our experiments show that f-BRS, fused with a depth estimation baseline, is trapped in local optima, and fails to improve the network predictions. To resolve that, we propose a double-stage adaptive refinement scheme (DARS). In the first stage, a Delaunay-based correction module significantly improves the depth generated by a baseline network. In the second stage, a particle swarm optimizer (PSO) delineates the estimation through fine-tuning f-BRS parameters—that is, scales and biases. DARS is evaluated on an outdoor benchmark, KITTI, and an indoor benchmark, NYUv2 while for both the network is pre-trained on KITTI. The proposed scheme outperformed rival methods on both datasets.

The Coronavirus outbreak that began in December, 2019 became a worldwide pandemic by March, 2020. The education industry had to adapt to this new change in a speedy and most feasible way by shifting to virtual classes over the internet and other available resources. WhatsApp has turned out to be a boon in academic’s section where in all the teachers have their own subject-wise groups on the said application. This not only helps them to share the necessary information resources but also to have discussion regarding the subject matter. On the other side, this application allows easy access for the students to all the resources shared by the teacher, and they can share their assignments without much difficulty with their subject teachers. Therefore, it has become a primary tool for conducting teaching, learning and evaluation online. The researchers have tried to analyze impact of online classes and the efforts required by the students to learn online with the help of survey conducted with the sample size of 514. The survey questionnaire was grouped into 4 categories namely; Opinion on Information and Communications Technology (ICT) based Teaching, Changes in communication behavior due to ICT using WhatsApp, the main hindrance for integration of ICT (Information Communication Technology) in the teaching-learning process and disadvantages of using ICT for teaching and learning.

GANs are well known for success in the realistic image gen-eration. However, they can be applied in tabular data generation as well.We will review and examine some recent papers about tabular GANs inaction. We will generate data to make train distribution bring closer tothe test. Then compare model performance trained on the initial traindataset, with trained on the train with GAN generated data, also wetrain the model by sampling train by adversarial training. We show thatusing GAN might be an option in case of uneven data distribution be-tween train and test data

In this paper, we propose a novel network representation learning model TransPath to encode heterogeneous information networks (HINs). Traditional network representation learning models aim to learn the embeddings of a homogeneous network. TransPath is able to capture the rich semantic and structure information of a HIN via meta-paths. We take advantage of the concept of translation mechanism in knowledge graph which regards a meta-path, instead of an edge, as a translating operation from the first node to the last node. Moreover, we propose a user-guided meta-path sampling strategy which takes users' preference as a guidance, which could explore the semantics of a path more precisely, and meanwhile improve model efficiency via the avoidance of other noisy and meaningless meta-paths. We evaluate our model on two large-scale real-world datasets DBLP and YELP, and two benchmark tasks similarity search and node classification. We observe that TransPath outperforms other state-of-the-art baselines consistently and significantly.

Recent advancements in neural machine translation (NMT) offer promising potential for generating cross-language clinical natural language processing (NLP) resources. There is a pressing need to be able to foster the development of clinical NLP tools that extract key clinical entities in a comparable way for a multitude of medical application scenarios, hindered by lack of multilingual annotated data. This study explores the efficacy of using NMT and annotation projection techniques with expert in the loop validation to develop named entity recognition (NER) systems for an under resourced target language (Catalan) by leveraging Spanish clinical corpora annotated by domain experts. We employed a state-of-the-art NMT system to translate three clinical case corpora. The translated annotations were then projected onto the target language texts and subsequently validated and corrected by clinical domain experts. The efficacy of the resulting NER systems was evaluated against manually annotated test sets in the target language. Our findings indicate that this approach not only facilitates the generation of high-quality training data for the target language (Catalan) but also demonstrates the potential to extend this methodology to other languages, thereby enhancing multilingual clinical NLP resource development. The generated corpora and components are publicly accessible, providing potentially a valuable resource for further research and application in multilingual clinical settings: https://zenodo.org/doi/10.5281/zenodo.13133124.

Background: In recent years, computational aesthetics and neuroaesthetics have provided novel insights into understanding beauty. Building upon the findings of traditional aesthetics, this study aims to combine these two research methods to explore an interdisciplinary approach to studying aesthetics; Method: Abstract artworks were used as experimental materials. Based on traditional aesthetics and in combination, features of composition, tone, and texture were selected. Computational aesthetic methods were then employed to correspond these features to physical quantities: blank space, gray histogram, GLCM, LBP, and Gabor filters. An EEG experiment was carried out, in which participants conducted aesthetic evaluations of the experimental materials in different contexts (genuine, fake), and their EEG data was recorded to analyze the impact of various feature classes in the aesthetic evaluation process. Finally, a SVM was utilized to model the feature data, EEG data, context data, and subjective aesthetic evaluation data; Result: Behavioral data revealed that higher aesthetic ratings in the genuine context. EEG data indicated that genuine contexts elicited more negative deflections in the prefrontal lobes between 200-1000ms. Class II compositions demonstrated more positive deflections in the parietal lobes at 50-120ms, while Class I tones evoked more positive amplitudes in the occipital lobes at 200-300ms. Gabor features showed significant variations in the parieto-occipital area at an early stage. Class II LBP elicited a prefrontal negative wave with a larger amplitude. The results of the SVM models indicated that the model incorporating aesthetic subject and context data (ACC=0.76866) outperforms the model using only parameters of the aesthetic object (ACC=0.68657); Conclusion: A positive context tends to provide participants with a more positive aesthetic experience, but abstract artworks may not respond to this positivity. During aesthetic evaluation, the ERP data activated by different features show a trend from global to local. The SVM model based on multimodal data fusion effectively predicts aesthetics, further demonstrating the feasibility of the combined research approach of computational aesthetics and neuroaesthetics.

A typical orchard's mechanical operation consists of three or four stages: lining, digging for plantation, moving the seedling from nurseries to the farm, moving the seedling to the planting hole, and planting the seedling in the hole. However, the digging the planting hole is the most time-consuming operation. In fruit orchards, robots' usage is increasingly becoming more prevalent to increase operational efficiency. They offer practical and effective services to both industry and people, whether they are assigned to plant trees, reduce the use of chemical fertilizers, or carry heavy loads to relieve staff. Robots can operate for extended periods of time and can highly adept at repetitive tasks like planting many trees. The present study aims to identify the locations for planting trees in orchards using geographic information systems (GIS), to develop an autonomous drilling machine and use the developed robot to open planting holes. There isn't a comparable study on autonomous hole planting in the literature in this regard. The agricultural mobile robot is a four wheeled nonholonomic robot with differential steering and forwarding capability to stable target positions. The designed mobile robot can be used in fully autonomous, partially autonomous, or fully manual modes. The drilling system, which is a y-axis shifter driven by a DC motor with reducer includes an auger with a 2.1 HP gasoline engine. SOLIDWORKS software was used for designing and drawing of the mobile robot and drilling system. The Microsoft Visual Basic.NET programming language was used to create the robot navigation system and drilling mechanism software. The cross-track error (XTE), which determines the distances between the actual and desired holes positions, was utilized to analyze the steering accuracy of the mobile robot to the drilling spots. Consequently, the average of the arithmetic means was determined to be 4.35 cm, and the standard deviation was 1.73 cm. This figure indicates that the suggested system is effective for drilling plant holes in orchards.

In this project the EEG – electroencephalogram - channel(s) will be characterized to diagnose PTSD – Post-traumatic stress disorder – cases. For this aim, we applied boosting methods including a combination of K-mean and Support Vector Machine (SVM) models to find the feature weights to detect the PTSD cases. We classified 32 channels of 12 subjects including 6 PTSD and 6 healthy controls using a 6-mean classifier. The linear SVM found the weights of distinguished channels within each subject for each cluster. It was found that the significant SVM weights of F4, F8, and Pz are smaller in PTSD than in healthy subjects. This new method can be used as a tool to better understand the interaction of EEG signals and diagnosis.

Genotypic testing is often recommended to improve the management of patients infected with human immunodeficiency virus (HIV). To help combat this major pandemic, next-generation sequencing (NGS) techniques are widely used to analyse resistance to antiretroviral drugs. In this study, we used a Vela Sentosa kit, which is usually used for the Ion Torrent personal genome machine (PGM) platform, to sequence HIV using the Illumina Miseq platform. After RNA extraction and reverse transcriptase-polymerase chain reaction (RT-PCR), minor modifications were applied to the Vela Sentosa kit to adapt it to Illumina Miseq platform. Analysis of the results showed the same mutations present in the samples using both sequencing platforms. The total number of reads varied from 185,069 to 752,343 and from 642,162 to 2,074,028 in the Ion Torrent PGM platform and the Illumina Miseq platform, respectively. The average depth was 21955 and 46856 for Ion Torrent PGM and Illumina Miseq platforms, respectively. The cost of sequencing a run of eight samples was closely similar between the two platforms (about 1 790 United States dollars [USD] for Illumina Miseq and about 1833 USD for Ion Torrent PGM platform). We have shown for the first time that it is possible to adapt and use the Vela Sentosa kit for the Illumina Miseq platform to obtain high quality results with a similar cost.

The relative position of the orchard robot to the rows of fruit trees is an important parameter for achieving autonomous navigations. The current methods for estimating the position parameters between rows of orchard robots obtain low parameter accuracy, and to address this problem, this paper proposes a machine vision-based method for detecting the relative position of orchard robots and fruit tree rows. Firstly, the fruit tree trunk is identified based on the improved YOLOv4 model; secondly, the camera coordinates of the tree trunk are calculated from the principle of binocular camera triangulation, and the ground projection coordinates of the tree trunk are obtained through coordinate conversion; finally, the midpoints of the projection coordinates of different sides are combined and the navigation path is obtained by linear fitting with the least squares method, and the position parameters of the orchard robot are obtained through calculation. The experimental results show that the average accuracy and average recall of the improved YOLOv4 model for fruit tree trunk detection are 97.05% and 95.42%, respectively, which are 5.92 and 7.91 percentage points higher than those of the original YOLOv4 model. The average errors of heading angle and lateral deviation estimates obtained based on the method in this paper are 0.57° and 0.02 m. The method can accurately calculate heading angle and lateral deviation values at different positions between rows, and can provide a reference for autonomous visual navigation of orchard robots.

Like the most of crops, especially sugarcane needs to be kept upright until it is harvested. Because, lodging of sugarcane has a significant negative effect on cane yield and sugar content of sugarcane. To keep sugarcane upright earthing up is an utmost intercultural operation. In Bangladesh, most of the operations for sugarcane cultivation including earthing up are generally done in traditional method using human labor which increases production costs as well as reduces the income of sugarcane growers. So, a cost effective two-wheeled tractor (2WT) mounted earthing up machine was developed in Bangladesh Sugarcrop Research Institute (BSRI), Pabna to reduce drudgery and cost of sugarcane production. Field tests were conducted in experimental sugarcane field at BSRI and technical and economic performances of the developed earthing up machine were also carried out based on the field test. Average effective field capacity and field efficiency were found 0.16 ha/hr and 77.41 %, respectively for the developed earthing up machine. The earthing up machine was not found economically viable when it is used only for earthing up operation. Besides, when the 2WT was being used as the main driver for other activities including earthing up operation, then the earthing up machine becomes economically beneficial with net cash flow, net present value, internal rate of return, benefit-cost ratio and payback period of BDT 148497/ha, BDT 23184, 3%, 3.81:1 and approximately 1 year, respectively. On the contrary, considering cost of only earthing up tool without 2WT, then it was found economically beneficial with net cash flow, internal rate of return, net present value, benefit-cost ratio and payback period of BDT 16428/ha, BDT 3053, 4.7%, 2.71:1 and approximately 2 years, respectively. Since 2WT is commonly used for versatile farming purposes. Therefore, versatile use of 2WT as prime mover for other machines including earthing up machine can make earthing up machine economically viable and beneficial for sugarcane growers.

Conducting related research is crucial since there are still many problems that need to be resolved in the research on soft robots in the areas of material selection, structure design and manufacture, and drive control. Soft manipulators, a subset of soft robots, are now a popular area of study for many researchers. In comparison to typical manipulators, soft manipulators feature a high degree of gripping flexibility and a basic morphological structure. They are composed of flexible materials. It has a wide range of potential applications in healthcare, rehabilitation, bionics, and detection, and it can compensate for the drawbacks of rigid manipulators in some use scenarios. A modular soft-body torsional gripping system is developed after a torsional and gripping actuator is conceived, constructed, and its performance is examined. The torsion actuator and the grasping actuator can be combined in the system in a modular fashion. With the help of RGB-D vision algorithms, this multi-modular setup makes it possible to combine soft actuators with various twisting degrees and achieve exact gripping. Through pneumatic control, the target object is precisely grasped and rotated at various angles, enabling rotation of the target object in three dimensions.

Background: There is an increasing interest in the role of EEG in neurorehabilitation. We primarily aimed to identify the knowledge base through highly influential studies. Our secondary aims were to imprint the relevant thematic hotspots, research trends, and social networks within the scientific community. Methods: We performed an electronic search in Scopus looking for studies reporting on rehabilitation in patients with neurological disabilities. The most influential papers outlined the knowledge base, while a word co-occurrence analysis imprinted the research hotspots. Likewise, co-citation analyses highlighted collaboration networks between Universities, authors, and countries. The results were presented in summary tables, burst detection plots, and geospatial maps. Finally, a content review based on the top-20 most cited articles completed our study. Results: Our current bibliometric study was based on 874 records from 420 sources. There was a vivid research interest in EEG use for neurorehabilitation, with an annual growth rate as high as 14.3%. The most influential paper was the study titled "Brain-computer interfaces, a review" by Nicolas-Alfonso LF and Gomez-Gill J, with 997 citations, followed by "Brain-computer interfaces in neurological rehabilitation" by Daly J. and Wolpaw JR (708 citations). The USA, Italy, and Germany were among the most productive countries. The research hotspots shifted with time from the use of “functional magnetic imaging” to EEG-based “brain-machine interface”, “motor imagery”, and “deep learning”. Conclusions: EEG constitutes the most significant input in brain-computer interfaces (BCI) and can be successfully used in the neurorehabilitation of patients with stroke, amyotrophic lateral sclerosis, and traumatic brain and spinal injury. EEG-based BCI facilitates training, communication, and control of wheelchair and exoskeletons. However, research is limited to specific scientific groups from developed countries. Evidence is expected to change with the broader availability of BCI and improvement in EEG filtering algorithms.

Stripe rust ​​(caused by Puccinia striiformis f. sp. tritici) is one of the most devastating diseases of wheat and causes large-scale epidemics and severe yield loss. Applying fungicides during early epidemic development is crucial to controlling the disease but is often challenged by resource-limited human visual scouting. Deep learning has the potential to process images and videos captured from affordable devices to empower high-throughput phenotyping for early detection of stripe rust for timely application of fungicides and improve control efficiency. Here, we developed RustNet, a neural network-based image classifier, for efficiently monitoring fields for stripe rust. RustNet was built on a ResNet-18 architecture pre-trained with ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) dataset using transfer learning. RGB images and videos of multiple wheat fields with different wheat types (winter and spring wheat), conditions (irrigated and non-irrigated), and locations were acquired using smartphones or unmanned aerial vehicles near the canopy. A semi-automated image labeling approach was conducted to improve labeling efficiency by combining automated machine labeling and human correction. Cross-validations across multiple categories (sensor platforms, wheat types, and locations) achieved Area Under Curve from 0.72 to 0.87. Independent validation on a published dataset from Germany achieved accuracies ranging from 0.79 to 0.86. The visualization of the last convolutional layer of RustNet demonstrated the identification of pixels with stripe rust. RustNet is freely available at https://zzlab.net/RustNet.

In the present study, we investigate the post-editese phenomenon, i.e., the unique features that set machine translated post-edited texts apart from human-translated texts. We use two literary texts, namely, the English children's novel by Lewis Carroll Alice’s Adventures in Wonderland (AW) and Paula Hawkins' popular book The Girl on the Train (TGOTT) translated from English into Brazilian-Portuguese to investigate whether the post-editese features can be found on the surface of the post-edited (PE) texts. In addition, we examine how the features found in the PE texts differ from the features encountered in the human-translated (HT) and machine translation (MT) versions of the same source text. Results revealed evidence for post-editese for TGOTT only with PE versions being more similar to the MT output than to the HT texts.

Background: Gastric cancer (GC) is one of the leading malignancy diseases worldwide, especially in Asian. CAST is a potential oncogene in GC carcinogenesis process. The character of macrophage infiltration in GC microenvironment was also unaddressed. Methods: We first applied machine searching in gene candidate evaluation of GC. CAST expression was analyzed via the Human Protein Atlas (HPA) and Gene Expression Profiling Interactive Analysis 2 (GEPIA2) database. Protein-protein interaction (PPI) network was downloaded from STRING. We investigated the impact of CAST on clinical prognosis using Kaplan-Meier plotter. The correlations between CAST and Lgr5 and macrophage infiltration in GC was surveyed via TIMER 2.0. Finally, GeneMANIA was also used to evaluate the possible functional linkage between genes. Results: After machine-assisted searching, CAST expression was found signicant difference in the overall survival of GC patients. STRING revealed CAST related proteomics and transcriptomics associations, mainly about CAPN family. Moreover, CAST significantly impacts the prognosis of GC from other datasets validation. Notably, high CAST expression was correlated with worse overall survival in GC patients (hazard ratio = 1.59; logrank P = 9.4 x 10-8). CAST and Lgr5 expressions were both positively correlated with WNT 2 and WNT 2B. Among GC patients in several datasets, CAST and macrophage infiltration evaluated together showed no obvious trend toward poor clinical overall survival. Conclusion: CAST plays an important role in GC clinical prognosis and is associated with WNT 2/WNT 2B/Lgr5. Our study denmostrated that CAST in GC overall survival is regulated by macrophage infiltration.

The color and NIR spectrum are key to build an oil estimation model, thus it requires individual olives clustering before the Sohlext oil extraction method can be applied. The objective was to analyze an OC estimation model of individual olives, based on cluster of similar color and NIR spectrum in different combination of the first and/or the second season. This study was performed with Chilean Arbequina olives in 2016 and 2017. The descriptor of the cluster consisted of the 3 color channels of c1, c2, c3 color model plus 11 reflectance points between 1710 and 1735 nm of each olive, normalized with the Z-score index. Clusters of similar color and NIR spectrum were formed with the k-means++ algorithm, leaving a sufficient amount of olives to be able to perform the Sohlext analysis of OC, as reference value. The estimation models were based on the Support Vector Machine. The test was carried out with the Leave One-Out Cross Validation in different training-testing combinations. The best model predicted the OC with 6% and 13%deviation respect to the real value in one season by itself and when one season tested with another season, respectively. The use of clustering in estimation model is discussed.

Precision agriculture is a technology used by farmers to help food sustainability amidst growing population. One of the tools of precision agriculture is yield monitoring, which helps a farmer manage his production. Yield monitoring is usually done during harvest, however it could also be done early in the growing season. Early prediction of yield, specifically for fruit trees, aids the farmer in the marketing of their product and assists in managing production logistics such as labor requirement and storage needs. In this study, a machine vision system is developed to estimate fruit yield early in the season. The machine vision system uses a color camera to capture images of fruit trees during the full bloom period. An image segmentation algorithm based on an artificial neural network was developed to recognize and count the blossoms on the tree. The artificial neural network segmentation algorithm uses color information and position as input. The resulting correlation between the blossom count and the actual number of fruits on the tree shows the potential of this method to be used for early prediction of fruit yield.

Machine learning (ML) methodologies have been looked upon recently as a potential candidate for mitigating nonlinearity issues in optical communications. In this paper, we experimentally demonstrate a 40-Gb/s 256-quadrature amplitude modulation (QAM) signal-based Radio over Fiber (RoF) system for 50 km of standard single mode fiber length which utilizes support vector machine (SVM) decision method to indicate an effective nonlinearity mitigation. The influence of different impairments in the system is evaluated that includes the influences of Mach-Zehnder Modulator nonlinearities, in-phase and quadrature phase skew of the modulator. By utilizing SVM, the results demonstrated in terms of bit error rate and eye linearity suggest that impairments are significantly reduced and licit input signal power span of 5dBs is enlarged to 15 dBs.

In the fashion field, the use of electroplated small metal parts such as studs, clips and buckles is widespread. The plate is often made of precious metal, such as gold or platinum. Due to the high cost of these materials, it is strategically relevant and of primary importance for manufacturers to avoid any waste by depositing only the strictly necessary amount of material. To this aim, Companies need to be aware of the overall number of items to be electroplated so that it is possible to properly set the parameters driving the galvanic process. Accordingly, the present paper describes a Machine Vision-based method able to automatically count small metal parts arranged on a galvanic frame. The devised method relies on the definition of a proper acquisition system and on the development of image processing-based routines. Such a system is then implemented on a counting machine is meant to be adopted in the galvanic industrial practice to properly define a suitable set or working parameters (such as current, voltage and deposition time) for the electroplating machine and, thereby, to assure the desired plate thickness from one side and to avoid material waste on the other.

In this paper, modification of dual-Halbach permanent magnet (PM) array is investigated to improve performance of tubular linear machine, in terms of flux density and output power. Instead of a classical Halbach array with only radial and axial PMs, proposed model involves insertion of mig-magnets, which have magnetized angle shifted from the reference magnetized angles of axial and radial PMs. This structure leads to elimination of flux leakage and concentration of flux linkage in middle of the coil; therefore, the performance of machine is increased.

Neural microprobes represent an important component of neural prosthetic systems where implanted microprobes record the electro-potentials generated by specific thoughts in the brain and convey the signals to algorithms trained to interpret these thoughts. Here, we present novel elongated multi-site neural probe that can reach depths greater than 10mm. We hypothesize that reaching such depth allows the recording of cognitive signals required to drive cognitive prosthetics. The impedance of the recording sites on the probes was on the order of 500 kΩ at 1 kHz, which is consistent with probes used for neurophysiological recordings. The probes were made porous using Xenon Difluoride (XeF₂) dry etching to improve the biocompatibility and their adherence to the surrounding neural tissue. Numerical studies were performed to determine the reliability of the porous probes. We implanted the elongated probe in rats and show that the elongated probes are capable of simultaneously recording both spikes and local field potentials (LFPs) from various recording sites.

COVID-19 was a terrible worldwide pandemic that caused a global public health crisis, with numerous deaths and a severe economic depression. To suppress the spread of COVID-19 and initiate patient isolation and contact tracing to reduce its effect, early diagnosis was required, with real-time reverse transcriptase polymerase chain reaction (RT-PCR) swab test being the most widely used. However, the RT-PCR test was sometimes found to be lengthy and inaccurate and; for that reason, in many cases of severe complications of COVID-19 pneumonia, chest screening with radiography imaging was preferred. In this paper, we carried out a study for COVID-19 detection from computed tomography images, and compared the obtained results using deep learning (DL) and support vector machine (SVM). The findings showed that, despite the excellent results shown by deep learning, the accuracy in predicting COVID-19 using SVM, in the presence of small databases, was slightly higher than DL. The execution time using SVM was also shorter

This study explored the incidence of metaphorical virtual classrooms and interactive learning objects in the interaction of students in online mode. The main objective was to analyze how these digital tools, driven by a set of strategies to promote their use, affect the interaction of students in the virtual classroom system and their derived effects. To this end, the latest version of Moodle was implemented in conjunction with gamification plugins and interactive tools in the higher education institution used as a case study. The methodology consisted of data collection through ordinal instruments applied to the teachers and student performance metrics gathered using a plugin developed to extract accurate metrics of each student's usage and performance through direct queries to the Moodle database and its processing through a neural network. This facilitated the collection of standardized data on the actual metrics of each virtual classroom at the end of the teaching of each subject from both the previous LMS and the newly implemented one. This data was then analyzed using advanced statistical techniques, including Mahalanobis distances, confirmatory factor analysis, and the Wilcoxon signed-rank test. These methods provided a compelling comparison between the old and new systems, revealing significant improvements in the metrics and factors evaluated. The results showed a significant improvement in teachers' perceptions of the usability of the virtual classroom system and an increase in students' academic performance, interaction, progress, and time spent learning in virtual contexts. These results provide solid empirical evidence of the added value of these educational tools as effective strategies for improving student interaction, performance, and motivation in online education.

The advent of deep learning (DL) has revolutionized medical imaging, offering unprecedented avenues for accurate disease classification and diagnosis. DL models have shown remarkable promise for classifying brain tumor from Magnetic Resonance Imaging (MRI) scans. However, despite their impressive performance, the opaque nature of DL models poses challenges in understanding their decision-making processes, particularly crucial in medical contexts where interpretability is essential. This paper explores the intersection of medical image analysis and DL interpretability, aiming to elucidate the decision-making rationale of DL models in brain tumor classification. Leveraging state-of-the-art DL frameworks with transfer learning, we conduct a comprehensive evaluation encompassing both classification accuracy and interpretability. Using state-of-the-art DL frameworks with transfer learning, we conduct a thorough evaluation covering both classification accuracy and interpretability. We employ adaptive path-based techniques to understand the underlying decision-making mechanisms of these models. Grad-CAM and Grad-CAM++ highlight critical image regions where the tumors are located.

In recent years, the viability of employing multi-agent reinforcement learning technology for adaptive traffic signal control has been extensively validated. However, owing to restricted communication among agents and the partial observability of the traffic environment, the process of mapping road network states to actions encounters numerous challenges. To address this problem, this paper proposes a multi-agent deep reinforcement learning model with an emphasis on communication content (CMARL). The model decouples the complex relationships between multi-signal agents through centralized training and decentralized execution. Specifically, we first pass the traffic state through an improved deep neural network to achieve the extraction of high-dimensional semantic information and the learning of the communication matrix. Then the agents selectively interact with each other based on the learned communication matrix and generate the final state features. Finally, the features are inputted to the QMIX network to achieve the final action selection. We compare the CMARL model with 6 other baseline algorithms in real traffic networks. The results show that CMARL can significantly reduce vehicle congestion, and run stably in various scenarios.

This study addressed the need for efficient data collection in micro-mobility using low-end hardware, focusing on developing a system capable of handling large real-time data streams. We proposed a novel data collection system that leverages incremental learning techniques, enabling AI-based services for micro-mobility passengers through smartphones. Our approach utilizes 3-axis acceleration sensors integrated into micro-mobility devices, collecting motion data in real-time. This data is processed through an incremental learning pre-processing server, employing the Broad Learning System algorithm, to ensure robust performance in noisy, real-world environments. The use of incremental learning is pivotal, allowing our system to adapt continuously to new data, enhancing the accuracy and relevance of the AI services provided to passengers. This research not only advances the technical capabilities in micro-mobility data handling but also has the potential to enhance the overall passenger experience through improved AI-based services.

When analyzing user geospatial information through deep learning methods, it is typically necessary to annotate existing geospatial data. Currently, manual annotation methods are commonly employed, suffering from issues related to low efficiency and accuracy. This design is based on the TensorFlow deep learning framework and first realizes the BiLSTM+CRF+AGG deep learning model. Among the models, AGG is the aggregation layer, which is introduced to solve the problem of solid particle size equilibrium. Secondly, based on the characteristics of original data and professional data, an automatic labeling algorithm is proposed. The algorithm first preprocesses the acquired original data set and professional data set, The most valuable unlabeled data set which can make the training model converge quickly is selected from the original data set as the target data set. Sort the target data set based on preset rules and set annotation parameters for the sorted target data set. Based on the set annotation parameters, the corpus is synthesized and used as the annotation result. Thirdly, based on the active learning strategy, a manual annotation auxiliary scheme is proposed, and an Excel generation module that is convenient for manual annotation correction is designed and developed to further improve the efficiency and quality of annotation through iterative processing. The combination of the BiLSTM+CRF+AGG deep learning model and high-quality annotation can accurately identify non-standard, incomplete, or even incorrect geographical information entities. This annotation method has found successful practical application within the context of the research project and has been granted an invention patent.

Abstract:The objects of fine-grained image categories(e.g., bird species) are various subclass under different categories. Because the differences between subclass are very subtle and most of them are concentrated in multiple local areas, the task of fine-grained image recognition is very challenging. At the same time, some fine-grained networks tend to focus on a certain region when judging the target category, resulting in the lack of other auxiliary regional features. To this end, Inception V3 is used as the backbone network, and an enhanced and complementary fine-grained image classification network is designed. While adopting the method of reinforcement learning to obtain more detailed fine grain image features, the complementary network can obtain the complementary discriminant area of the target through the method of attention erasure to increase the network's perception of the overall target. Finally, experiments are conducted on CUB-200-2011, FGVC Aircraft and Stanford dogs three open datasets. The experimental results show that the proposed model has better performance.

A topic of growing interest in urban remote sensing is the automated extraction of geometrical building information for 3D city modeling. Roof geometry information is useful for applications such as urban planning, solar potential estimation and telecommunication installation planning, and wind flow simulations for pollutant diffusion analysis. Recent research has proven that the advance in remote sensing technologies and deep learning methods offer the prospects of deriving the roof structure information accurately and efficiently. In this study, we propose a Vectorized Roof Extractor- method based on Fully Convolutional Networks (FCNs) and advanced polygonization method to extract roof structure from aerial imagery and a normalized Digital Surface Models (nDSM) in a regularized vector format. The roof structure consists of building outlines, external edges of the building roof, inner rooflines, internal intersections of the main roof planes. The methodology is comprised of segmentation, vectorization and post-processing for outer rooflines, external edges of the building roof, and inner rooflines, and internal intersections of the main roof planes. For the comparison, we adapt the Frame field Learning (FFL) method originally designed to extract building polygons [1]. Our experiments are conducted on a custom data set derived for the city of Enschede, The Netherlands, using aerial imagery, nDSM and manually digitized training polygons. The results show that the proposed Vectorized Roof Extractor outperformed adapted FFL on PoLiS distance with values of 3.5 m and 1.2 m for outlines and inner rooflines, respectively. Furthermore, the model surpassed the adapted FFL on PoLiS-thresholded F-score for outlines and inner rooflines, with 0.31 and 0.57, respectively. The Vectorized Roof Extractor produced adequate visual results, with straighter walls and fewer missed inner roofline detections. It can predict buildings with common walls thanks to skeleton graph computation. To summarize, the proposed method is suitable for urban applications and has the potential to be improved further.

"Finding fresh water in the ocean of data." is a challenge that all deep learning domains struggle with, especially in the area of hyperspectral image analysis. As hyperspectral remote sensing technology advances by leaps and bounds, there are increasing amounts of hyperspectral images(HSIs) can be available. Whereas in fact, these unlabeled HSIs are powerless to be used as material to driven a supervised learning task due to the extremely expensive labeling costs and some unknown regions. Although learning-based methods have achieved remarkable performance due to their superior ability to represent features, at the cost, these methods are complex, inflexible and tough to carry out transfer learning. In this paper, we propose the "Instructional Mask AutoEncoder"(IMAE), which is a simple and powerful self-supervised learner for HSI classification that uses a transformer-based mask autoencoder to extract the general features of HSIs through a self-reconstructing agent task. Moreover, we utilize the metric learning to perform an instructor which can direct the model focus on the human interested region of the input so that we can alleviate the defects of transformer-based model such as local attention distraction, lack of inductive bias and tremendous training data requirement. In downstream forward propagation, instead of global average pooling, we employ a learnable aggregation to put the tokens into fullplay. The obtained results illustrate that our method effectively accelerates the convergence rate and promotes the performance in downstream task.

The Kuwaiti dialect is a particular dialect of Arabic spoken in Kuwait; it differs significantly from standard Arabic and the dialects of neighboring countries in the same region. Few research papers with a focus on the Kuwaiti dialect have been published in the field of NLP. In this study, we created Kuwaiti dialect language resources using Q8VaxStance, a vaccine stance labeling system for a large dataset of tweets. This dataset will fill this gap and provide a valuable resource for researchers studying vaccine hesitancy in Kuwait. Furthermore, it will contribute to the Arabic natural language processing field by providing a dataset for developing and evaluating machine learning models for stance detection in the Kuwaiti dialect. The proposed vaccine stance labeling system combines the benefits of weak supervised learning and zero-shot learning; for this purpose, we implemented 52 experiments on 42815 unlabeled tweets extracted between December 2020 and July 2022. The results of the experiments show that using keyword detection in conjunction with zero-shot model labeling functions is significantly better than using only keyword detection labeling functions or just zero-shot model labeling functions. Furthermore, using the Arabic language in both the labels and prompt or a mix of Arabic labels and an English prompt is statistically significant compared to using English in both the labels and prompt for the total number of generated labels evaluation metric. Finally, the best accuracy for Macro-F1 values were found in the experiments KHZSLF-EE4 and KHZSLF-EA1, with values of 0.83 and 0.83, respectively. And, for the total automatically labeled data evaluation metric, experiment KHZSLF-EE4 labeled 42,270 tweets, while experiment KHZSLF-EA1 was able to generate 42,764 labels.

Bone metastasis detection and quantification on bone scintigraphy is challenging and clinical important for treatment and patient’s life quality. To develop a CNN based diagnostic system for automated segmentation on bone metastasis regions is non-trivial, especially for a small dataset. A dataset in house comprising 100 breast cancer patients and 100 prostate cancer patients is utilized for this research. The Double U-Net model is adapted through the integration of background removal, adding negative samples, and transfer learning methods for bone metastasis detection. The performance is investigated via 10-fold cross-validation and computed in pixel-wise scale. The best model we achieved has precision of 63.08%, sensitivity of 70.82%, and F1-score of 66.72%. The developed system has the potential to provide pre-diagnostic reports for physicians in final decisions and the calculation of the bone scan index (BSI) with the combination with bone skeleton segmentation.

Industrial data scarcity is one of the largest factors holding back the widespread use of machine learning in manufacturing. To overcome this problem, the concept of transfer learning was developed and it achieved high attention in recent industrial research. Our paper focuses on the problem of time series segmentation and presents the first in-depth research about transfer learning for deep-learning based time series segmentation on the example of industrial end-of-line pump testing. In particularly, we investigate if the performance of deep learning models can be increased by pretraining the network with data from other domains. Three different scenarios are analyzed: source and target data being closely related, source and target data being distantly related, and source and target data being non-related. The results demonstrate that transfer learning can enhance the performance of time series segmentation models in respect to accuracy and training speed. The benefit is most clearly seen in scenarios where source and training data are closely related and the number of target training data samples is lowest. However, in the scenario of non-related datasets, cases of negative Transfer Learning were observed as well. Thus, the research emphasizes the potential, but also the challenges of industrial Transfer Learning.

Protein phosphorylation and ADP-ribosylation (ADPr), as two types of post-translational modifications (PTM), are the process of adding phosphate group and ADP-ribose moieties to proteins, respectively. Although both PTM types can occur on many amino acid types, serine is the most common. Serine phosphorylation (pS), serine ADPr (SADPr), and their in situ crosstalks (pSADPr) play essential roles in biological processes. Although in silico classifiers have been developed for predicting pS and SADPr sites, the classifier for predicting pSADPr sites is unavailable. In this study, we developed classifiers to predict pSADPr sites. Specifically, we collected 3250 human pSADPr, 7520 SADPr, 151,227 pS and 80,096 unmodified serine sites. Based on them, we investigated the characteristics of pSADPr sites and constructed three classifiers to predict pSADPr sites from the pS dataset, the SADPr dataset and the protein sequences separately. We built and evaluated five deep-learning classifiers in ten-fold cross-validation and independent test datasets. Three of them (e.g. Convolutional Neural Network with the One-Hot encoding, dubbed CNNOH) performed better than the rest two. For instance, CNNOH had the AUC values of 0.700, 0.914 and 0.954 for recognizing pSADPr sites from the SADPr, pS and unmodified serine sites.Therefore, it is challenging to distinguish pSADPr sites from SADPr sites compared to the other two. It is consistent with our observation that pSADPr's characteristics are more similar to those of SADPr than the rest. Furthermore, we used the classifiers as base classifiers to develop a few stacking-based ensemble classifiers to improve performance. However, none of the ensemble classifiers showed better performances, suggesting that the base classifiers have good enough performances. Finally, we developed an online tool for extensively predicting human pSADPr sites based on the CNNOH classifier, dubbed EdeepSADPr. It is freely available through http://edeepsadpr.bioinfogo.org/.

Coronavirus disease since December 2019 has significantly affected millions of people. Given the effect this disease has on the pulmonary systems of humans, there is a need for chest radiographic imaging (CXR) for monitoring the disease and preventing further deaths. Several studies have been shown that Deep Learning models can achieve promising results for COVID-19 diagnosis towards the CXR perspective. However, this research field is at an initial stage since there is a limited number of large CXR repositories regarding COVID-19. In this study, five deep learning models were analyzed and evaluated with the aim of identifying COVID-19 from chest X-Ray images. More specifically, we utilized the ResNet50, ResNet101, DenseNet121, DenseNet169 and InceptionV3 using Transfer Learning. All models were trained and validated on the largest publicly available repository for COVID-19 CXR images. Furthermore, they were evaluated on unknown data as well, that was not used for training or validation, authenticating their performance, and clarifying their usage in a medical scenario. All models achieved satisfactory performance where ResNet101 was the superior model achieving 96% in Precision, Recall, and Accuracy. Our outcomes show the potential of deep learning models on COVID-19 medical offering a promising way for the deeper understanding of COVID-19.

The keyless systems have replaced the old fashion methods of inserting physical keys in the keyhole to, i.e., unlock the door, because they are inconvenient and easy to be exploited by the threat actors. Keyless systems use the technology of radio frequency (RF) as an interface to transmit signals from the key fob to the vehicle. However, Keyless systems are susceptible to being compromised by a thread actor who intercepts the transmitted signal and performs a reply attack. In this paper, we propose a transfer learning-based model to identify the replay attacks launched against remote keyless controlled vehicles. Specifically, the system makes use of a pre-trained ResNet50 deep neural network to predict the wireless remote signals used to lock or unlock doors of a remote-controlled vehicle system remotely. The signals are finally classified into three classes: real signal, fake signal high gain, and fake signal low gain. We have trained our model with 100 epochs (3800 iterations) on a KeFRA 2022 dataset, a modern dataset. The model has recorded a final validation accuracy of 99.71% and a final validation loss of 0.29% at a low inferencing time of 50 ms for the model-based SGD solver. The experimental evaluation revealed the supremacy of the proposed model.

Online reinforcement learning (RL) algorithms are increasingly used to personalize digital interventions in the fields of mobile health and online education. Common challenges in designing and testing an RL algorithm in these settings include ensuring the RL algorithm can learn and run stably under real-time constraints, and accounting for the complexity of the environment, e.g., a lack of accurate mechanistic models for the user dynamics. To guide how one can tackle these challenges, we extend the PCS (Predictability, Computability, Stability) framework, a data science framework that incorporates best practices from machine learning and statistics in supervised learning (Yu and Kumbier, 2020), to the design of RL algorithms for the digital interventions setting. Further, we provide guidelines on how to design simulation environments, a crucial tool for evaluating RL candidate algorithms using the PCS framework. We illustrate the use of the PCS framework for designing an RL algorithm for Oralytics, a mobile health study aiming to improve users' tooth-brushing behaviors through the personalized delivery of intervention messages. Oralytics will go into the field in late 2022.

Regardless of country and age, the importance of history education is always being emphasized. Although the importance of history education is being emphasized in Korea, there are many difficulties in getting students to understand history properly through school classes alone, and it is also difficult to attract students to participate in classes. The effectiveness of education using games has been proven 20 years ago, and the demand for game-based education is gradually increasing in the current education world, which is becoming more open. In this paper, based on the effects proven through research on the existing game-based education, the improvement of historical thinking ability, experiential history learning, and the problems of game-based education introduced in the ESN report and the discomfort of teachers who participated in the education were improved. A plan was suggested to select and use games suitable for basic education. In this thesis, we selected a history game with a clear historical and periodic background and without distortion of history, and experimented with teaching using games focusing on historical thinking and empirical history learning. The learning achievement of textbook-based education was compared.

Regardless of country and age, the importance of history education is always being emphasized. Although the importance of history education is being emphasized in Korea, there are many difficulties in getting students to understand history properly through school classes alone, and it is also difficult to attract students to participate in classes. The effectiveness of education using games has been proven 20 years ago, and the demand for game-based education is gradually increasing in the current education world, which is becoming more open. In this paper, based on the effects proven through research on the existing game-based education, the improvement of historical thinking ability, experiential history learning, and the problems of game-based education introduced in the ESN report and the discomfort of teachers who participated in the education were improved. A plan was suggested to select and use games suitable for basic education. In this thesis, we selected a history game with a clear historical and periodic background and without distortion of history, and experimented with teaching using games focusing on historical thinking and empirical history learning. The learning achievement of textbook-based education was compared.

In software development, developers received bug reports that describe the software bug. Developers find the cause of bug through reviewing the code and reproducing the abnormal behavior that can be considered as tedious and time-consuming processes. The developers need an automated system that incorporates large domain knowledge and recommends a solution for those bugs to ease on developers rather than spending more manual efforts to fixing the bugs or waiting on Q&A websites for other users to reply to them. Stack Overflow is a popular question-answer site that is focusing on programming issues, thus we can benefit knowledge available in this rich platform. This paper, presents a survey covering the methods in the field of mining software repositories. We propose an architecture to build a recommender System using the learning to rank approach. Deep learning is used to construct a model that solve the problem of learning to rank using stack overflow data. Text mining techniques were invested to extract, evaluate and recommend the answers that have the best relevance with the solution of this bug report.

We propose a novel transfer learning method for speech emotion recognition allowing us to obtain promising results when only few training data is available. With as low as 125 examples per emotion class, we were able to reach a higher accuracy than a strong baseline trained on 8 times more data. Our method leverages knowledge contained in pre-trained speech representations extracted from models trained on a more general self-supervised task which doesn’t require human annotations, such as the wav2vec model. We provide detailed insights on the benefits of our approach by varying the training data size, which can help labeling teams to work more efficiently. We compare performance with other popular methods on the IEMOCAP dataset, a well-benchmarked dataset among the Speech Emotion Recognition (SER) research community. Furthermore, we demonstrate that results can be greatly improved by combining acoustic and linguistic knowledge from transfer learning. We align acoustic pre-trained representations with semantic representations from the BERT model through an attention-based recurrent neural network. Performance improves significantly when combining both modalities and scales with the amount of data. When trained on the full IEMOCAP dataset, we reach a new state-of-the-art of 73.9% unweighted accuracy (UA).

Deep learning models are part of the family of artificial neural networks and, as such, it suffers of catastrophic interference when they learn sequentially. In addition, most of these models have a rigid architecture which prevents the incremental learning of new classes. To overcome these drawbacks, in this article we propose the Self-Improving Generative Artificial Neural Network (SIGANN), a type of end-to-end Deep Neural Network system which is able to ease the catastrophic forgetting problem when leaning new classes. In this method, we introduce a novelty detection model to automatically detect samples of new classes, moreover an adversarial auto-encoder is used to produce samples of previous classes. This system consists of three main modules: a classifier module implemented using a Deep Convolutional Neural Network, a generator module based on an adversarial autoencoder; and a novelty detection module, implemented using an OpenMax activation function. Using the EMNIST data set, the model was trained incrementally, starting with a small set of classes. The results of the simulation show that SIGANN is able to retain previous knowledge with a gradual forgetfulness for each learning sequence. Moreover, SIGANN can detect new classes that are hidden in the data and, therefore, proceed with incremental class learning.

In order for robots to attain more general-purpose utility, grasping is a necessary skill to master. Such general-purpose robots may use their perception abilities in order to visually identify grasps for a given object. A grasp describes how a robotic end-effector can be arranged on top of an object to securely grab it between the robotic gripper and successfully lift it without slippage. Traditionally, grasp detection requires expert human knowledge to analytically form the task-specific algorithm, but this is an arduous and time-consuming approach. During the last five years, deep learning methods have enabled significant advancements in robotic vision, natural language processing, and automated driving applications. The successful results of these methods have driven robotics researchers to explore the application of deep learning methods in task generalised robotic applications. This paper reviews the current state-of-the-art in regards to the application of deep learning methods to generalised robotic grasping and discusses how each element of the deep learning approach has improved the overall performance of robotic grasp detection. A number of the most promising approaches are evaluated and the most successful for grasp detection is identified as the one-shot detection method. The availability of suitable volumes of appropriate training data is identified as a major obstacle for effective utilisation of the deep learning approaches, and the use of transfer learning techniques is identified as a potential mechanism to address this. Finally, current trends in the field and future potential research directions are discussed.

The current study characterizes the transient M/M/1 queue manifold info-geometrically, through devising Fisher Information matrix(FIM) and its inverse(IFIM). Additionally, the impact of stability on the existence of IFIM and explore the geodesic equations of motion has been revealed. More potentially, the paper discusses some info-geometric applications to Machine Learning are highlighted. Closing remarks with some challenging open problems combined with the next phase of research are given.

The combination of artificial intelligence algorithms and numerical methods has recently become popular in the prediction of macroscopic and microscopic hydrodynamics parameters of bubble column reactors. The multi inputs and outputs machine learning can cover small phase interactions or large fluid behavior in industrial domains. This numerical combination can develop the smart multiphase bubble column reactor with the ability of low-cost computational time. It can also decrease case studies for the optimization process when big data is appropriately used during learning. There are still many model parameters that need to be optimized for a very accurate artificial algorithm, including data processing and initialization, the combination of inputs and outputs, number of inputs and model tuning parameters. For this study, we aim to train four inputs big data during learning process by an adaptive neuro-fuzzy inference system or adaptive-network-based fuzzy inference system (ANFIS) method, and we consider the superficial gas velocity as one of the input variables, while for the first time, one of the computational fluid dynamics (CFD) outputs named gas velocity is used as an output of the artificial algorithm. The results show that the increasing number of input variables improves the intelligence of the ANFIS method up to , and the number of rules during learning process has a significant effect on the accuracy of this type of modeling. The results also show that propper selection of model parameters results in more accuracy in prediction of the flow characteristics in the column structure.

Recently, there has been, on the one hand, an increase in the complexity of digital device designs and, on the other hand, an increase in the requirements for the development time and the reliability of the designs. One of the directions of solving this problem is developing new techniques for designing digital devices.This paper proposes a new technique for designing digital devices based on finite state machines with datapath (FSMD), when the functioning of the device is described in the form of an algorithm state machine with datapath (ASMD) charts. The new technique is called ASMD-FSMD. Different digital device design techniques are compared to each other using design examples of a synchronous multiplier on field programmable gate array (FPGA). The efficiency of the ASMD-FSMD technique compared to the traditional approach in terms of area and performance was investigated. The ASMD-FSMD technique, compared to the traditional one, reduces the area from 28.6% to 39.7% and increases the speed for some designs to 17.6%. In addition, using the ASMD-FSMD technique significantly reduces design time and increases design reliability. In conclusion, recommendations for using the ASMD-FSMD technique are made.

Background: Ovarian, cervical, and endometrial cancers stand as fatal health killers for women's mental and physical health, especially affecting female reproductive systems. Exploiting weakly supervised learning and explainable AI techniques are crucial for fast, accurate, and robust automatic marker detection, efficient prevention, and primary treatment of gynecological tumors. Methods: Weakly supervised learning and deep learning-based schemes, are investigated in the cross-subject fields of clinical diagnostic imaging and explainable AI technology. Related methods, opening research problems and challenging subjects are explored on the screening and treatment of gynecological tumors and performing cancer image diagnosis in the latest study. Results: Keynote approaches combining ultrasound medicine, AI, and clinical imaging technology are summarized. Combining learning-based schemes with medical imaging, prospective insights are put forward for refreshed concepts on treatments in the area of gynecological oncology, with a feasible range of applications for their corresponding AI techniques. Conclusions: Explainable AI and deep learning-based approaches are capable of performing accurate classification between benign and malignant tumors, yielding a pathway to care for women's health, improving the survival rate of patients, pacing with disease prediction, and matching the strategic goal of "Healthy China 2030".

Hyperspectral small target detection (HSTD) is a promising pixel-level detection task. However, due to the low contrast and imbalance number between the target and background spatially and high dimensions spectrally, it is a challenging one. To address these issues, this work proposes a representation learning-based graph and generative network for hyperspectral small target detection. The model builds a fusion network through frequency representation for HSTD, where the novel architecture incorporates irregular topological data and the spatial-spectral feature to improve its representation ability. Firstly, a graph convolutional network (GCN) module better models the non-local topological relationship between samples to represent the hyperspectral scene’s underlying data structure. The mini-batch-training pattern of the GCN decreases the high computational cost of building an adjacency matrix for high-dimensional data sets. In parallel, the generative model enhances the differentiation reconstruction and the deep feature representation ability with respect to the target spectral signature. Finally, a fusion module compensates for the extracted different types of HS features and integrates their complementary merits for hyperspectral data interpretation while increasing detection and background suppression capabilities. Experiments on different hyperspectral data sets demonstrate the advantages of the proposed architecture.

This research presents the Cross-Cultural Intelligent Language Learning System (CILS), a novel approach integrating Artificial Intelligence (AI) into language education to enhance cross-cultural communication. CILS utilizes advanced AI technologies to provide adaptive, personalized learning experiences that cater to the unique linguistic and cultural backgrounds of each learner. By dynamically adjusting content and methodology, CILS significantly improves linguistic proficiency and cultural understanding, essential for effective global interactions. The implementation of CILS in platforms such as Busuu and HelloTalk has demonstrated marked improvements in engagement and communication skills among learners. Empirical studies validate the system's effectiveness in real-world settings, showing enhanced learner performance and increased intercultural competence. Additionally, the Technology Acceptance Model (TAM) applied confirms that the usability and perceived usefulness of AI-driven systems strongly influence learner acceptance and sustained use. This study not only underscores the potential of AI in transforming language education but also highlights the critical role of cultural sensitivity in designing educational technologies.

This research introduces a pioneering solution to the challenges posed by gastrointestinal tract (GI) cancer in radiation therapy, focusing on the imperative task of precise organ segmentation for minimizing radiation-induced damage. GI imaging has historically used manual demarcation, which is laborious and uncomfortable for patients. We address this by introducing the ResECA-U-Net deep learning model, a novel combination of the UNet and ResNet34 architectures. Furthermore, we further augment its functionality by incorporating the Efficient Channel Attention (ECA-Net) methodology. By utilizing data from the UW-Madison Carbone Cancer Centre, we carefully investigate several image processing techniques designed to capture critical local characteristics. With its foundation in computer vision concepts, the ResECA-U-Net model is excellent at extracting fine details from GI images. Sophisticated metrics such as intersection over union (IoU) and the dice coefficient are used to evaluate performance. Our study's outcomes demonstrate the effectiveness of the suggested method, yielding an impressive 96.27% Dice coefficient and 91.48% IoU. These results highlight the significant contribution that our strategy has made to the advancement of cancer therapy. Beyond its scientific merits, this work has the potential to significantly enhance cancer patients' quality of life and provide better long-term outcomes. Our work is a significant step towards automating and optimizing the segmentation process, which can potentially change how GI cancer is treated completely.

With the popularity of solar energy in the electricity market, demand arises for data such as precise locations of solar panels for efficient energy planning, management, and distribution. However, this data is not easily accessible and in some cases, information such as precise locations does not exist. Furthermore, existing data sets for training semantic segmentation models of PV installations are limited, and their annotation is time-consuming and labor-intensive. Therefore, for additional remote sensing (RS) data creation, the pix2pix generative adversarial network (GAN) is utilized, enriching the original resampled training data of varying GSDs without compromising its integrity. Experiments done with the DeepLabV3 model, ResNet-50 backbone, and pix2pix GAN architecture were conducted to find the optimal configuration for an accurate RS imagery segmentation model. The result is a fine-tuned solar panel semantic segmentation model, trained using transfer learning and utilizing an optimal amount – 60% of generated RS imagery for additional training data, increasing model accuracy. The findings demonstrate the benefits of using GAN-generated images as additional training data, increasing the size of small data sets, and improving the capabilities of the segmentation model for solar panel detection in RS images.

With the widespread Application of Virtual Reality (VR) in education, optimizing foreign language learning in VR has become a focal point of research. This paper introduces a comprehensive theoretical framework (VR-CCL) based on constructivism and cognitive load theory to enhance foreign language learning in VR. Through a literature review, we explore the applications of VR in education, foreign language learning theories, and prior works on technology-assisted language learning. We further detail the three main components of the VR-CCL framework and validate its effectiveness through two case studies: Duolingo VR and Rosetta Stone VR. Finally, we discuss the strengths and limitations of the framework and its implications for educators and developers.

This paper presents a two-stage hierarchical neural network using image classification and object detection algorithms as key building blocks for a system that automatically detects a potential design right infringement. This neural network is trained to return the Top-N original design right records that highly resemble the input image of a counterfeit. Design rights specify the unique aesthetic characteristics of a product. Due to the rapid change of trends, new design rights are continuously generated. This work proposes an Ensemble Neural Network (ENN), an artificial neural network model that aims to deal with a large amount of counterfeit data and design right records that are frequently added and deleted. At first, we performed image classification and objection detection learning per design right using the existing models with a proven track record of high accuracy. The distributed models form the backbone of the ENN and yield intermediate results aggregated at a master neural network. This master neural network is a deep residual network paired with a fully connected network. This ensemble layer is trained to determine the sub-models that return the best result for a given input image of a product. In the final stage, the ENN model multiples the inferred similarity coefficients to the weighted input vectors produced by the individual sub-models to assess the similarity between the test input image and the existing product design rights to see any sign of violation. Given 84 design rights and the sample product images taken meticulously under various conditions, our ENN model achieved average Top-1 and Top-3 accuracies of 98.409% and 99.460%, respectively. Upon introducing new design rights data, a partial update of the inference model was done an order of magnitude faster than the single model. ENN maintained a high level of accuracy as it scaled out to handle more design rights. Therefore, the ENN model is expected to offer practical help to the inspectors in the field, such as the customs at the border that deal with a swarm of products.

Agriculture is one of the indispensable fields for the survival of mankind. Potatoes also have a significant role in the field of agriculture. The quality and quantity of potatoes are significantly impacted by several diseases, such as early blight and late blight, and manual interpretation of these leaf diseases is time-consuming and inconvenient. Fortunately, leaf appearance is used to detect diseases in potato plants. Productivity will considerably rise if the infections are detected early. Different types of image processing methods and machine learning methods are used for early recognition of those diseases from leaf images so that the product losses are decreased significantly. For the incredible and marvelous performance of CNN, it is the most popular deep learning method that is used immensely for the recognition of leaf diseases from images. Several pretrained deep learning models, such as VGG16, ResNet50, InceptionV3, MobileNetV2, Xception, and a deep learning model developed using CNN, are employed for potato leaf disease classification and recognition on the same dataset. The transfer learning technique is applied to the pretrained model and the data augmentation technique is applied to the Proposed CNN model for potato disease classification from leaf samples. Compared to pretrained models, the proposed CNN model offers the lowest loss and highest accuracy for potato leaf disease detection while using fewer parameters and layers. It achieves the best performance with a test accuracy of 99.33% compared to other Pretrained models used in the diagnosis of potato leaf disease.

Aiming at the problem of hypersonic morphing vehicle avoiding no-fly zones and reaching the target, an improved predictor-corrector guidance method is proposed. Firstly, the aircraft motion model and the constraint model are established. Then, the basic algorithm is given, the Q-learning method is used to design the attack angle and sweep angle scheme to ensure that the aircraft can fly over the low-altitude zones. The B-spline curve is used to design the location of flight path points and the bank angle scheme is designed according to the predictor-corrector method, so that the aircraft can fly around to avoid high-altitude zones. Next, Monte Carlo reinforcement learning(MCRL) method is used to improve predictor-corrector method and Deep Neural Network(DNN) is used to fit reward function. The improved method can generate trajectory with better performance. Simulation results verify the effectiveness of the proposed algorithm.

This study investigates how digital alchemy can enhance literature and language teaching through a combination of online and face-to-face learning. It uses constructivist learning theory and the SAMR model to examine how digital tools and resources can transform learner engagement, critical thinking, and creativity. The study gathered data from interviews, focus groups, and document analysis with 30 participants from private HEI schools. The results show that digital alchemy through blended learning allows learners to personalize and collaborate in their exploration of various literary texts. However, the study also identifies some challenges related to resource availability and educator training. The study emphasizes the importance of using digital alchemy in literature and language teaching and suggests some ways for educators, administrators, and policymakers to effectively use digital tools and resources for student-centered teaching methods in the digital era.

Every month teachers face the dilemma of what exercises should their students practice, and what their consequences are on long-term learning. Since teachers prefer to pose their own exercises, this generates a large number of questions, each one attempted by a small number of students. Thus, we couldn’t use models based on big data such as deep learning. Instead, we developed a simple to understand state-space model that predicts end-of-year national test scores. We used 2,386 online fourth-grade mathematic questions designed by teachers and each attempted by some of the 500 students in 24 low socioeconomic schools. We found that the state-space model predictions improved month-by-month and that in most months it outperformed linear regression models. Moreover, the state-space estimator provides for each month a direct mechanism to simulate different practice strategies and compute their impact on the end-of-year standardized national test. We built iso-impact curves based on two critical variables: the number of questions solved correctly in the first attempt and the total number of exercises attempted. This allows the teacher to visualize the trade-off between asking students to do exercises more carefully or doing more exercises. To the best of our knowledge, this model is the first of its kind in education. It is a novel tool that supports teachers drive whole classes to achieve long-term learning targets.

Freezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson’s Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used to help patients recover from FOG and resume normal gait. RAS might be ineffective due to the latency between the start of a FOG event, it’s detection and initialization of RAS. We propose a system capable of both FOG prediction and detection using signals from tri-axial accelerometer sensors that will be useful in initializing RAS with minimal latency. We compared the performance of several time frequency analysis techniques, including moving windows extracted from the signals, handcrafted features, Recurrence Plots (RP), Short Time Fourier Transform (STFT), Discreet Wavelet Transform (DWT) and Pseudo Wigner Ville Distribution (PWVD) with Deep Learning (DL) based Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN). We also propose three Ensemble Network Architectures that combine all the time frequency representations and DL architectures. Experimental results show that our ensemble architectures significantly improve the performance compared with existing techniques. We also present the results of applying our method trained on publicly available dataset to data collected from patients using wearable sensors in collaboration with A.T. Still University.