Species distribution modeling (SDM) has come a long way since its inception. Starting as simple bioclimatic envelope models based on expert knowledge, species distribution models (SDMs) have evolved into complex and sophisticated models that incorporate multiple sources of data and machine learning algorithms. Today, SDMs play a crucial role in addressing pressing conservation and management issues, including the impacts of climate change on species ranges and the as-sessment of species vulnerability to extinction. In this article, we will embark on a journey through the history, present, and future of SDM, exploring its evolution from bioclimatic envelopes to machine learning. We will also provide practical tips on how to use SDMs effectively and discuss the exciting future developments in this field. Whether you are a seasoned SDM expert or new to this field, this article will provide valuable insights into the exciting world of SDM. By exploring the rich history and current state of the field, we hope to shed light on the tremendous potential of SDM for improving our understanding of the distribution of species in a changing world.

The rise of the Internet has enabled people to express their opinions on various subjects through social media, blogs, and website comments. As a result, there has been a significant increase in research on sentiment analysis. However, most of the research efforts have focused on analyzing sentiment in English-language data, neglecting the wealth of information available in other languages. In this paper, we provide a comprehensive review of the current state-of-the-art in multilingual sentiment analysis. The survey investigates techniques for data preprocessing, representation learning, and feature extraction in multilingual sentiment analysis. It explores cross-lingual transfer learning, domain adaptation, and data augmentation methods that enhance the performance of sentiment analysis models, particularly in low-resource languages and domains. It provides insights into the state-of-the-art approaches, challenges, and opportunities in this evolving field and encourages further advancements in multilingual sentiment analysis research.

Cricket, the most popular sports in the world to chase by the fans. Many cricket fans are interested in analyzing the elements and activities that affect the outcomes of matches. Machine learning in sports analytics is a relatively new topic in computer science. The purpose of this survey is to anticipate the outcome of a PSL champion team and build a winning strategy. Machine learning (ML) has exhibited favorable outcomes in a variety of sectors for diverse prediction using classification, regression, and so on, and is proven to be accurate. The innovative frameworks based on ML have the ability to learn from previous experiences. The cricket pitch is the most important aspect, alongside home game an edge, coin toss, innings of play, day/night match, physical conditioning, and dynamic plans, among other things. The dataset from previously ESPN Cricifno was used for this purpose. Recent classification approaches including, Random Forest, Gradient Boost, Deep Neural Networks used to conduct a comparative analysis based on their results and performances, as well as team strategies.

Deep learning-based question answering systems have transformed the discipline of natural language processing (NLP) by automating the extraction of answers from textual data. This survey paper provides a captivating overview of these systems, exploring methodologies, techniques, and architectures such as recurrent neural networks (RNNs), BERT model, and transformer models. Extractive and generative approaches are examined, alongside the challenges of handling complex questions, managing noisy input, and addressing rare or unseen words. This survey serves as a stimulating reference, offering valuable insights to researchers and practitioners, fueling innovation and advancement in question answering systems within NLP.

When training deep neural networks tasks, the most popular choices are cross-entropy loss. On the other hand, in general speaking, a decent loss function can take on shapes that are considerably more flexible and ought to be adapted for different activities and datasets. In most of the classification tasks, generally if the true class is not correctly recognized by the network (top1), that class is placed among the five classes with the highest probability (top5). This shows that the network does not necessarily recognize the correct class with a low probability, but a class similar to it (such as 3 vs. 8 in mnist) assigns a higher probability and this causes a mistake in that task. Accordingly, we proposed a loss function deals with the error of class that the neural network incorrectly recognized as correct, in addition to the correct class error. We call our proposed loss as False Positive Loss (FPL), with the intention of viewing and designing loss functions not only through the utilization of true class but also through the utilization of the value of false positive classes. One of the core properties of our proposed loss is full adaptability, which makes False Positive Loss be fully capable of getting reformulated by using other widely used loss functions formulas based on the task or the need of the users. Extensive experimental results demonstrate that our suggested loss function outperforms other well-known losses on a variety of tasks and datasets. As can be observed, the performance of our False Positive Loss is superior to that of the cross-entropy loss when it comes to tasks involving 2D picture classification. We have compared our loss with cross entropy as the most common classification loss function on some models (such as ResNet-18, ResNet-50 and Efficientnet-V2) through classification known as a basic computer vision task. with both random or pre-trained initial weights. As a result, in some cases the models with our loss outperform the same tasks with cross entropy from the viewpoint of some metric (i.e. accuracy and FP). For example, the resnet-50 on cifar-10 dataset with random initialization indicated a top1 accuracy of 94.93 with cross entropy and 95.25 with our loss, while for top5 accuracy the results are 99.86 and 99.87, respectively.

Zero-shot learning ability robotics enables robots to generalize their knowledge and perform tasks for which they have not been explicitly trained. This ability is extremely helpful because in classic learning approaches, robots are trained on specific tasks and require extensive data and labeled examples to perform accurately. However, in real-world scenarios, robots often encounter new or unseen tasks that were not part of their training data. We briefly survey works in this area to give the reader a perspective about progresses in this area.

Maintaining the judiciary's power requires a high level of budgetary expenditure, but the specifics of this relationship have yet to be fully explored. Although several studies have analyzed the impact of spending in the judiciary through productivity and performance-related measures, none have employed machine learning techniques. This study examines the productivity of the judiciary based on spending and other variables using machine learning techniques, including clustering and neural networks. The final neural network model supports the results of Pearson's parametric correlation test, which found no significant correlation between expenditure and productivity. This study's findings demonstrate the importance of understanding that increased public budgetary expenditure alone is insufficient for improving the judiciary's efficiency. Instead, other administrative and technical measures are necessary to meet the demands of the Brazilian judiciary and improve service delivery rates. These findings offer important theoretical and managerial contributions to the field.

Weather forecast has a big impact on the global economy, accurate and timely weather forecast is required by all, it affects many aspects of human livelihood and lifestyle, it also plays a critical role in decision making for severe weather management and for primary and secondary sectors like agriculture, transportation, tourism, and industry as they rely on good weather conditions for production and operations. The erratic and uncertain complex nature of the weather makes traditional weather forecasting tedious and a challenging task, traditional weather forecast involves applying technology and scientific knowledge on numerical weather prediction (NWP), and weather radar to solve complex mathematical equations to obtain forecasts based on current weather conditions. These traditional processes utilize expensive, complex physical and computational power to produce forecasts, which can be inaccurate and have various catastrophic impacts on society. In this research, a machine learning-based weather forecasting model was proposed, the model was implemented using 4 classifier algorithms which include Random Forest classifier, Decision Tree Algorithm, Gaussian Naïve Bayes model, and Gradient Boosting Classifier, these algorithms were trained using a publicly available dataset from Kaggle for the city of Seattle for the period 2012 to 2015. The model’s performance was evaluated; the Gaussian Naive Bayes algorithm proved to be the best performing algorithm with a predictive accuracy of 84.153 %.

Simple Learning Motivations Hierarchy Model (SLMHM) is a theory that attempts to structure the path of learning “growth” with 16 levels where each next level corresponds to higher aims, motives, results, and satisfaction of needs. The SLMHM has been developed to simplify design, control, and evaluate the learning processes. The SLMHM was first presented at IES-2020 Conference (Gakh, 2020). More detailed research including analysis of internal structure shows that the model should be corrected. The “Plan-Do-Check-Act” cycle (PDCA Cycle) is popular in management. This paper describes the SLMHM improvements based on analyses of its similarities with the PDCA Cycle. The description of this research makes SLMHM more comprehend.

Human Activity Recognition (HAR) is a process to automatically detect human activities based on stream data generated from various sensors, including inertial sensors, physiological sensors, location sensors, cameras, time, and many others. Unsupervised contrastive learning has been excellent, while the contrastive loss mechanism is less studied. In this paper, we provide a temperature (τ) variance study affecting the loss of SimCLR model and ultimately full HAR evaluation results. We focus on understanding the implications of unsupervised contrastive loss in context of HAR data. In this work, also regulation of the temperature(τ) coefficient is incorporated for improving the HAR feature qualities and overall performance for downstream tasks in healthcare setting. Performance boost of 1.3% is observed in experimentation.

The past is an important lesson for facing the future with greater awareness. In this context, school plays a key role to spread knowledge on natural phenomena and to promote behavior change. Together with researchers, teachers can be strong allies to build more resilient future citizens. The Istituto Nazionale di Geofisica e Vulcanologia (INGV) school training activities provide tools to get ready for the next earthquake and/or tsunamis. About 5000 students from both Middle schools (ISCED 2) and High schools (ISCED 3) were involved in active learning activities based on a flipped-up approach during special online scientific events in the Pandemic. Online lab activities were conducted respectively during the European Researchers’ Night (“Earthquakes: history teaches us the future: researchers for a day with experimentation in didactics for ESL”) and during the World Water Day 2021 and the World Earth Day 2021 (“Tsunamis: history teaches us the future researchers for a day with experimentation in didactics for ESL”). These two Episodes of Situated Learning (ELS) experiences triggered students’ interest, favoring remote learning, developing life skills, focusing on historical seismic studies of both past earthquakes and tsunamis.

The design of school environments plays a pivotal role in promoting student wellness, mindfulness, and socio-emotional learning (SEL). This article explores the integration of Environment Behaviour Studies (EBS) concepts into school design to enhance students' overall well-being and academic success. It highlights the importance of indoor environmental quality, ergonomic and flexible learning spaces, and biophilic design in fostering a healthy and engaging learning atmosphere. Additionally, the article delves into the creation of mindfulness spaces, sensory-friendly environments, and the use of colour and aesthetics to support emotional regulation and mental health. By examining case studies of successful implementations, the article underscores best practices for designing schools that promote positive social interactions, ensure safety, and reflect community values. Ultimately, this comprehensive approach to school design aims to nurture holistic development, support socio-emotional learning, and prepare students for lifelong success.

The application of deep learning in autonomous vehicles has surged over the years with the advances in technologies. This research explores the integration of deep learning algorithms into autonomous vehicles (AVs), focusing on their role in perception, decision-making, localization, mapping, and navigation. It shows that deep learning, which as a part of machine learning, mimics the human brain's neural networks, enabling advancements in perception, decision-making, localization, mapping, and overall navigation. Techniques like convolutional neural networks are used for image detection and steering control, while deep learning is crucial for path planning, automated parking, and traffic maneuvering. Localization and mapping are essential for AVs' navigation, with deep learning-based object detection mechanisms like Faster R-CNN and YOLO proving effective in real-time obstacle detection. Apart from the roles, the study also revealed that integration of deep learning in AVs faces challenges such as dataset uncertainty, sensor challenges, and model training intricacies. However, these issues can be addressed through increased standardization of sensors, real-life testing for model training, and advancements in model compression technologies can optimize the performance of deep learning in AVs. The study concludes that deep learning plays a crucial role in enhancing the safety and reliability of AV navigation. This study contributes to the ongoing discourse on the optimal integration of deep learning in AVs, aiming to foster their safety, reliability, and societal acceptance.

This study focused on the predictive models incorporating machine learning techniques that induce new dynamics for forecasting energy generation, enabling effective planning, financing, and system monitoring. The research developed a machine learning-based power generation prediction model tailored explicitly for Kenya's Garissa solar power plant. The selected model demonstrated a root mean squared error of 5.23 during evaluation, resulting in a prediction accuracy of 90.42%. This high accuracy indicates that the model can be relied upon for precise generation prediction, facilitating effective planning, and system performance monitoring

In cotton cultivars, an insect that causes irreversible damage is the Spodoptera frugiperda, known as the fall armyworm. Since the visual detection of plants is a burdensome task for human inspection, the spectral information related to plant damage, registered on a spectral scale, can be useful. These measurements, associated with machine learning techniques, produce useful information for a rapid and non-invasive inspection method development. To contribute to this gap fulfillment, this paper proposes a machine learning framework to model the spectral response of cotton plants under the attack of the fall armyworm. Additionally, a theoretical model is presented, built from the results of the machine learning analysis, to infer this damage with up-to-date orbital sensors. The data was composed of the reflectance measurements collected at a cotton field with control plants and plants submitted to Spodoptera frugiperda damage. Their spectral response was recorded with a hand-held spectroradiometer ranging from 350 to 2,500 nm, for eight consecutive days. Different machine learning models were evaluated and the overall best model was defined by accuracies comparisons on a testing-set. A ranking approach was adopted based on the model accuracy, returning the most contributive wavelengths for the classification. Sequentially, an unsupervised neural network (Self-Organizing Map - SOM) was implemented to reduce data-dimensionality and assist in the definition of important spectral regions. The regions were associated with the spectral bands of the two sensors (OLI and MSI) and a theoretical model using a band simulation process with the overall best machine learning model was proposed. The results indicated that the Random Forest (RF) algorithm is the most suitable to predict cotton-plants damaged by insects and that the last day of analysis (8th day) was better to separate it, with F-measure equals 0.912. The ranking approach combined with the SOM method indicated the spectral regions at the red to near-infrared (650 to 1,350 nm) and shortwave infrared (1,570 to 1,640 nm) as the most important regions to the analysis. The proposed theoretical model simulated with the OLI and MSI sensor-bands returned an F-Measure of 0.865 and 0.886, respectively. In conclusion, this framework can be used to map cotton-plants under insect-attack. The theoretical model presents high accuracy to infer the insect-damaged on cotton plants based on multispectral bands from other sensors, being a useful tool for future research that intends to evaluate it in other areas and at different field scales.

Current conventional methods of evaluating microstructures are characterized by a high degree of subjectivity and a lack of reproducibility. Modern machine learning (ML) approaches have already shown great potential in overcoming these challenges. Once trained with representative data in combination with an objective ground truth, the ML model is able to perform a task properly in a reproducible and automated manner. However, in highly complex use cases, it is often not possible to create a definite ground truth. This study addresses this problem using the underlying showcase of microstructures of highly complex quenched and quenched and tempered (Q/QT) steels. A patch-wise classification approach combined with a sliding window technique provides a solution for segmenting entire microphotographs where pixel-wise segmentation is not applicable due to the problem of reproducibly creating unambiguous training masks. Using correlative microscopy, consisting of light optical microscope (LOM) and scanning electron microscope (SEM) micrographs as well as corresponding data from electron backscatter diffraction (EBSD), a training dataset of reference states that covers a wide range of microstructures was acquired in order to train accurate and robust ML models. Despite the enormous complexity associated with the steels treated here, classification accuracies of 88.8% in the case of LOM images and 93.7% for high-resolution SEM images were achieved. These high accuracies are close to super-human performance, especially in consideration of the reproducibility of the automated ML approaches compared to conventional methods based on subjective evaluations through experts.

False positives on multiparametric (mp)-MRI result in a large number of unnecessary biopsies in men with clinically insignificant diseases. This study investigates whether quantitative diffusion MRI can improve differentiation between false positives, true positives and normal tis-sue. Twenty-three patients underwent mp-MRI and Vascular, Extracellular and Restricted Diffu-sion for Cytometry in Tumours (VERDICT)-MRI, followed by transperineal biopsy. The patients were categorised into two groups following biopsy: (1) significant cancer - true positive (2) atro-phy/inflammation/high-grade prostatic intraepithelial neoplasia (PIN) - false positive. The clinical apparent diffusion coefficient (ADC) values of the lesions were obtained, and the intravoxel inco-herent motion (IVIM), diffusion kurtosis imaging (DKI) and VERDICT models were fitted using a deep learning approach. Significant differences (p < 0.05) between true positive and false positive lesions were found in ADC, IVIM perfusion fraction (f) and diffusivity (D), DKI diffusivity (DK) and kurtosis (K) and VERDICT intracellular volume fraction (fIC), extracellular-extravascular vol-ume fraction (fEES) and diffusivity (dEES) values. Significant differences between false positives and normal tissue were only found for the VERDICT fIC. These results demonstrate that model-based diffusion MRI could reduce the number of unnecessary biopsies due to false positive prostate lesions and shows promising sensitivity to benign diseases that mimic cancer.

Sunn pest is one of the most crucial noxious species in agriculture. As the sunn pest penetrates and makes damage to the grains, they can no longer be utilized to make bakery goods like bread, pasta, and other baked foods since they become unusable. Therefore, analysis and detection of damaged wheat grains are necessary for production to continue. We recommend that the dataset could be used for analysis and segmentation of the wheat grains, detection of the sunn pest damage condition, and classification of the 6 species of which the dataset consists. As mentioned, in our dataset, there are 6 different species of wheat, including Bezostaja, Müfitbey, Nacibey, Sönmez-2001, Tosunbey, and Ekiz, which are the species that were made in Türkiye. Our dataset differs from the others due to its various species and the condition, whether it is healthy or sunn pest damaged or broken wheat grain, and because the dataset is a multiclass one, it can be used for the classification of the varieties. On the other hand, when the sunn pest damage condition is taken into account, the dataset is suitable for the detection of the sunn pest damage. In addition to that, the dataset includes grains that touch each other which makes it more applicable to problems that arise in real-life. The dataset consists of 83 sunn pest damaged and 87 healthy wheat images. In addition, there are 170 images that contain 3565 wheat grains. As can be observed, the dataset contains a variety of wheat species with sunn pest affected which displays that the promised dataset is suitable for numerous machine learning problems such as classification, segmentation, and detection.

Variational Auto-Encoders (VAEs) are deep generative models used for unsupervised learning, however their standard version is not topology-aware in practice since the data topology may not be taken into consideration. In this paper, we propose two different approaches with the aim to preserve the topological structure between the input space and the latent representation of a VAE. Firstly, we introduce InvMap-VAE as a way to turn any dimensionality reduction technique, given an embedding it produces, into a generative model within a VAE framework providing an inverse mapping into original space. Secondly, we propose the Witness Simplicial VAE as an extension of the Simplicial Auto-Encoder to the variational setup using a witness complex for computing the simplicial regularization, and we motivate this method theoretically using tools from algebraic topology. The Witness Simplicial VAE is independent of any dimensionality reduction technique and together with its extension, Isolandmarks Witness Simplicial VAE, preserves the persistent Betti numbers of a data set better than a standard VAE.

A multicenter retrospective analysis of 408 patients diagnosed with onychomycosis and attended at three tertiary care Spanish hospitals was conducted to assess the effectiveness and safety of a combined treatment with ciclopirox 8% hydroxypropyl chitosan (CPX 8% HPCH) nail lacquer and oral antifungal agents (terbinafine, itraconazole, and fluconazole). Data were extracted and analyzed using the EHRead® technology based on natural language processing and machine learning and using SNOMED CT terminology. The median age was 51 years with a ratio male: female close to 1. Repeated nail trauma was the most common risk factor (7.1%). More than half of patients (56.6%) underwent fungal culture. Terbinafine was used in 67.7% of patients, itraconazole in 20.8%, and fluconazole in 11.5%. Treatment synchronicity distribution revealed that 59.1% of patients started concomitant treatment with CPX 8% HPCH and oral antifungals, 27.9% had initial oral antifungals, and 13% had initial nail lacquer. The response to treatment (positive response 15.7%, presumed positive 59.8%) was unrelated to treatment synchronicity or type of antifungal agent. Erythema (5.6%), diarrhea (4.9%) and fever (4.2%) were the most frequently registered potential adverse events. The present findings provide valuable insights for physicians paving the way for better management of patients with onychomycosis.

In the recent years, with the advent of Artificial Intelligence (AI) traditional methods have seen a significant transformation in the agriculture sector, especially in soil management. Soil management involves practices that maintains and improves the physical, chemical as well as the biological properties of the soil. Soil health management is essential for both the environmental conservation and sustainable agriculture production, ensuring the soil productivity and functional aspects associated with the ecosystem. Soil health management is one of the most important aspects of agriculture and food production, hence preserving and enhancing the soil health is an essential factor for supporting agriculture. Integration of Artificial Intelligence (AI) technologies with soil health management offers the potential to enhance agricultural sustainability, productivity, adapt to the climatic changes and resource constraints. The study of AI tools that can help improve soil health management by providing more accurate and efficient monitoring, analysis and decision-making capabilities. This paper studies the potential AI technologies including machine learning, robotics, and remote sensing in enhancing soil health, raising crop yields, and lowering environmental concerns by examining previous research and case studies.

The present research project entitled "Development of a method for predicting the optimal maturity level of avocado using machine learning" aims to establish an accurate and efficient approach to assess the maturity of avocados using machine learning methodologies. This research specifically focuses on identifying the relevant physical and chemical characteristics of avocados, creating a dataset containing categorized images of maturity levels, and creating machine learning models capable of accurately predicting fruit maturity. The studies reveal that the application of machine learning, in particular convolutional neural networks and multisensor models, has the potential to transform the prediction of avocado maturity and thus improve product quality and customer satisfaction. The findings indicate that the proposed techniques achieve an accuracy rate of over 90%, demonstrating their viability for integration into mobile applications that can benefit growers and suppliers in their decision-making processes.

This paper investigates the use of Physics-Informed Neural Networks (PINNs) in active learning cycles. We defined two scenarios: one semi-supervised and the other fully supervised. PINNs emphasize the integration of physical laws into neural networks to improve the predictive performance of vanilla neural networks and to enhance the efficiency of traditional methods for solving partial differential equations (PDEs). Key contributions include adapting existing computational frameworks to enable the use of Graph Neural Networks for solving problems that require the calculation of gradients on unstructured triangle meshes, a query strategy focusing on the physical loss, and a comparative analysis of this strategy against random sampling across both defined scenarios. This work establishes a foundation for future research aimed at expanding the application of Physics-Informed Graph Neural Networks (PIGNN) using active learning and addressing real-world problems in fluid dynamics and electrodynamics.

Incorporating knowledge graphs as auxiliary information to enhance recommendation systems can improve the representations learning of users and items. Recommendation methods based on knowledge graph can introduce user-item interaction learning into the item graph, focusing only on learning the node vector representations within a single graph; alternatively, they can treat user-item interactions and item graphs as two separate graphs and learn from each graph individually. Learning from two graphs has natural advantages in exploring original information and interaction information, but faces two main challenges: 1) in complex graph connection scenarios, how to adequately mine the self-information of each graph, and 2) how to merge interaction information from the two graphs while ensuring that user-item interaction information predominates. Existing methods do not thoroughly explore the simultaneous mining of self-information from both graphs and effective interaction information, leading to the loss of valuable insights. Considering the success of contrastive learning in mining self-information and auxiliary information, this paper proposes a dual-graph contrastive learning recommendation method based on knowledge graphs (KGDC) to explore a more accurate representations of users and items in recommendation systems based on external knowledge graphs. In the learning process within the self-graph, KGDC has strengthened and represented the information of different connecting edges in both graphs, and extracted the existing information more fully. In interactive information learning, KGDC reinforces the interaction relationship between users and items in the external knowledge graph, realizing the leading role of the main task. We have conducted a series of experiments on three standard datasets, and the results show that the proposed method can achieve better results.

This literature review delves into the realm of fault detection techniques for transmission lines, aiming to provide a comprehensive overview of recent advancements and key trends in the field. Employing a structured approach, the review synthesizes a plethora of research spanning from 2019 to 2024, sourced from diverse databases including IEEE Xplore, ScienceDirect, ResearchGate, Scopus, Litmaps, and Google Scholar. The methodology encompasses a systematic literature search protocol, stringent inclusion and exclusion criteria, meticulous data extraction, and a multi-dimensional analysis framework. The literature review uncovers a spectrum of fault detection methodologies, ranging from traditional signal processing techniques like Discrete Wavelet Transform and phase angle-based methods to cutting-edge deep learning algorithms such as Capsule Networks and Convolutional Neural Networks. Insights gleaned from the review underscore the critical importance of fault detection in maintaining the reliability, safety, and efficiency of power grids, highlighting its role as a frontline defense against widespread outages and equipment damage. Key findings from the review shed light on the efficacy of different fault detection approaches, showcasing their strengths and limitations across diverse system conditions. Furthermore, the review identifies common trends and challenges, including the need for real-world validation, scalability, adaptability to various network configurations, and cybersecurity considerations. This literature provides valuable insights and recommendations for future research endeavors in fault detection for transmission lines. By embracing advancements in both traditional and emerging techniques, researchers can continue to enhance the resilience and dependability of power transmission systems, ensuring their ability to withstand evolving challenges and safeguard critical infrastructure.

Recommendation systems are crucial in navigating the vast digital market. However, user data’s dynamic and non-stationary nature often hinders their efficacy. Traditional models struggle to adapt to the evolving preferences and behaviours inherent in user interaction data, posing a significant challenge for accurate prediction and personalisation. Addressing this, we propose a novel theoretical framework, the Non-stationary Transformer, designed to capture and leverage the temporal dynamics within data effectively. This approach enhances the traditional transformer architecture by introducing mechanisms accounting for non-stationary elements, offering a robust and adaptable solution for recommendation systems. Our experimental analysis, encompassing deep learning and reinforcement learning paradigms, demonstrates the framework’s superiority over benchmark models. The empirical results confirm the efficacy of our proposed framework, which not only provides significant performance enhancements, approximately 8% in Logloss reduction and up to 2% increase in F1 score but also underscores its potential applicability across accumulative reward scenarios. These findings advocate adopting Non-stationary Transformer models to tackle the complexities of today’s recommendation tasks.

Financial fraud poses a severe threat to the integrity of corporate financial statements and market efficiency. While auditors play a crucial role in detecting and preventing such fraud, the unique characteristics of this domain, including class imbalance, high misclassification costs, and am-biguous attributes, pose significant challenges. Traditional classification algorithms may not be optimally suited for this task. This paper proposes a novel stacking ensemble learning approach to enhanced detecting of Financial Statement Scam. By combining the strengths of multiple base learners, including Random Forest, XGBoost, and Gradient Boosting Decision Trees, our model leverages their diverse predictions to improve overall performance. A Logistic Regression me-ta-learner is employed to integrate the outputs of the base learners, capturing their collective wisdom while mitigating individual weaknesses. Extensive experimentation using a real-world dataset shown the superiority of our approach, achieving remarkable recall, precision, accuracy, and area under the curve metrics. The proposed model outperforms individual base learners, under-scoring the efficacy of ensemble learning in tackling the intricate problem of financial fraud detection. This research contributes to the creation of substantial and robust fraud detection systems, fostering trust and transparency in financial markets.

Facial acne is a prevalent dermatological condition regularly observed in the general population. This study introduces a novel deep learning model for facial acne segmentation utilizing a semi-supervised learning method known as bidirectional copy-paste, which synthesizes images by interchanging foreground and background parts between labeled and unlabeled images during the training phase. To overcome the lower performance observed in the labeled image training part compared to the previous methods, a new framework was devised to directly compute the training loss based on labeled images. The effectiveness of the proposed method was evaluated against previous semi-supervised learning methods using images cropped from facial images at acne sites. The proposed method achieved a Dice score of 0.5205 in experiments utilizing only 3% of labels, marking an improvement of 0.0151 to 0.0473 Dice score over previous methods. The proposed semi-supervised learning approach for facial acne segmentation demonstrates improvement in performance, offering a novel direction for future acne analysis.

The term "code smell" refers to an indication of a problem with the quality of source code. Numerous studies have been conducted to identify problematic features in source code. Initially, the focus was on utilizing metric-based and heuristic-based approaches. In recent years, however, there has been a shift towards using machine learning and deep learning (DL) techniques for smell detection. Nevertheless, the current algorithms are still considered to be in the early stages of development. Recognizing the challenges associated with identifying smells using DL methods, both academics and software developers have made efforts to address these obstacles. This work involves constructing and evaluating new DL models for code smell detection. Two models are built upon stacked autoencoders, employing a hybrid architecture that combines bidirectional long short-term memory and convolutional neural network components.

Prostate cancer is the second most frequent malignancy (after lung cancer) in men worldwide. Prostate tissue biopsies are usually graded using scores according to the Gleason grading system. This Gleason score is the most popular prognostic marker that reveals the potential aggressiveness of the disease. However, inter-observer variability in rating by human assessors is a major limiting factor. Such variability could lead to missing a severe case or suggesting unnecessary treatments. This study explores the discriminative ability of artificial intelligence (deep learning models) for Gleason score assessment. The study was designed to use whole-slide images of digitized H&E-stained biopsies of prostate tissues to automate the grading process and provide a remotely accessible clinical decision support system. Custom convolutional neural network architectures were trained on 10,616 images of prostate tissues. Gaussian filters were applied to pre-process the images and improve model performance. Transfer learning was applied to train eight machine learning architectures namely: Xception, VGG16 & 19, ResNet101, MobileNet, DenseNet121, EfficientNetB5 & B7. Efficient NetB7 had the best performance 85.2% compared with ground-truth classification by experts. Performance improves as more data is available. The model was deployed and hosted as a web application API on Google cloud service to ensure remote access. Tissue biopsy images can be uploaded and the corresponding Gleason score recovered immediately. This system reduces diagnostics turnaround time, increase throughput, and compensate for limited skills, especially in low resource settings.

The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an algorithm are well-informed and conforming to human understanding. Having ways to address these concerns is crucial in many domains, especially whenever humans and intelligent (physical or virtual) agents must cooperate in a shared environment. In this paper, we introduce an application of an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We show that from these policy graphs, policies for surrogate interpretable agents can be automatically generated. These policies can be used to measure the reliability of the explanations enabled by the PGs, through a fair behavioural comparison between the original opaque agent and the surrogate one. The contributions of this paper represent the first application of policy graphs in the context of explaining agent behaviour in collaborative multi-agent scenarios and presents experimental results that sets this kind of scenario apart from previous application in single-agent scenarios: when requiring collaborative behaviour, predicates that allow representing observations about the other agents are crucial to replicate the opaque agent’s behaviour and increase the reliability of explanations.

In areas where conventional fundus cameras are logistically unaffordable, the smartphone-based approach is considered as a promising future of glaucoma screening due to their affordability and ease-of-use. Optic disc localization is a critical stage during glaucoma screenings. For fundus images captured with standard fundus cameras, the majority of the models available out there can locate the optic disc with satisfactory performance. However, for images that are captured with smartphone-based fundus cameras, the inherent noise and lower quality of the fundus image makes it difficult for models to detect the optic disc region. In this study, we have proposed to utilize YOLOv8n for optic disc localization due to the model’s cutting-edge performance in diverse tasks and its lightweight nature. We have used a public dataset which has 2000 low quality fundus images that are captured using a smartphone-based fundoscopy device. From these, 60% of the data was used for fine-tuning the model, and 25% for testing. By using a confidence of 50% set as threshold, the model was able to detect the optic disc successfully on over 97% of test images with intersection over union of above 0.85. These results highlight the potential of the lightweight YOLOv8n model for deployment on resource-constrained environments, offering a promising performance on accurately localizing the OD and enhancing the feasibility of affordable glaucoma screening on smartphones.

Accurate and efficient medicinal plant image classification is of utmost importance as these plants produce a wide variety of bioactive compounds that offer therapeutic benefits. With a long history of medicinal plant usage, different parts of plants, such as flowers, leaves, and roots, have been recognized for their medicinal properties and are used for plant identification. However, leaf images are extensively used due to their convenient accessibility and are a major source of information. In recent years, transfer learning and fine-tuning, which use pre-trained deep convolutional networks to extract pertinent features, has emerged as an extremely effective approach for image identification problems. This study is leveraging the power of three component deep convolutional neural networks, namely VGG16, VGG19 and DenseNet201, to derive features from the input images of the medicinal plant dataset, containing leaf images of 30 classes. The models were compared and ensembled to make four hybrid models to enhance the predictive performance by utilizing the averaging and weighted averaging strategies. Quantitative experiments were carried out to evaluate the models on the Mendeley medicinal leaf dataset. The resultant ensemble of VGG19+DensNet201 with fine-tuning showcases enhanced capability in identifying medicinal plant images with an improvement of 7.43% and 5.8% compared with VGG19 and VGG16. Furthermore, VGG19+DensNet201 can outperform its standalone counterparts by achieving an accuracy of 99.12% on the test set. A thorough assessment with metrics such as accuracy, recall, precision, and f1-score firmly establishes the effectiveness of the ensemble strategy.

Authentic learning opportunities that simulate full scale design and construction experiences using real materials offer ideal experiential learning environments for construction and civil engineering students by challenging students to apply building concepts in practical settings. However, the excessive cost of real building materials required for this mode of education limits access to the vast majority of students. As a result, educational researchers have explored potential alternatives to provide cost-effective experiential learning through activities using mock-up materials (e.g., plastic straws, popsicle sticks) and simulation of experiences using immersive technologies (e.g., virtual reality or augmented reality). While some of these alternatives approximate the environment and others provide physical interaction with mock-up materials, the lack of authenticity in the building materials used introduces some apparent differences between the “authentic” learning environments and their cost-effective approximations. Therefore, this research aims to identify the learning processes reported by students and faculty who participated in authentic learning experiences to understand the ways in which this mode of education offers unique value to construction education. Their interview responses illustrated characteristics of authentic learning experiences that were believed to be critical to the learning process, some of which included: working in groups; interdisciplinary participants; and use of real construction materials. Although some of these characteristics are intrinsically linked to the use of real materials, others do not explicitly refer to interaction with real materials. This may indicate to aspects of the authentic learning processes that educational researchers can strategically target through more cost-effective learning environments like virtual and augmented reality. The contribution of this paper is in identifying the characteristics of authentic learning experiences that may guide educational investment and research innovations that aim to replicate some of these learning experiences through more accessible learning environments.

The IDS serves as a security system that maintains constant surveillance over network traffic and host systems in order to identify any security breaches or potentially concerning activities. Recently. the rise in cyber-attacks has driven the necessity for the development of automated and intelligent network intrusion detection systems. These systems are designed to learn the typical patterns of network traffic, allowing them to identify any deviations from normal behaviour, which can be classified as anomalous or malicious. Machine learning methods are widely used to exhibit a satisfactory effectiveness in detecting malicious payloads in the network traffic. While the volume of the data generated from IDS is increasing exponentially results in the emergence of substantial security risks, it highlighted the imperative to strengthen network security. The performance of traditional machine learning methods depends on the dataset and the data balance distribution in it. while most of IDS datasets suffer from unbalancing, this limits the performance of the machine learning method used in the system and results in missed detections and false alarms in the conventional IDSs. To address this issue, this paper presents a new model-based Generative Adversarial Network (GAN) called TDCGAN to enhance the detection rate of less of minor class in the dataset while maintaining efficiency. The proposed model consists of one generator and three discriminators with an election layer at the end of architecture. The UGR’16 data set is used for evaluation purposes. In order to demonstrate the efficacy of our proposed model, various machine learning algorithms have been utilized for comparison. The experimental findings have determined that TDCGAN presents an efficient resolution for addressing imbalanced intrusion detection and surpasses the performance of other oversampling machine learning methods.

This paper presents a study of an automated system for identifying planktic foraminifera at the species level. The system uses a combination of deep learning methods, specifically Convolutional Neural Networks (CNNs), to analyze digital images of foraminifera taken at different illumination angles. The dataset is composed of 1437 groups of sixteen grayscale images, one group for each foraminifer, that are then converted to RGB images with various processing methods. These RGB images are fed into a set of CNNs, organized in an Ensemble Learning (EL) environment. The ensemble is built by training different networks using different approaches for creating the RGB images. The study finds that an ensemble of CNN models trained on different RGB images improves the system's performance compared to other state-of-the-art approaches. The proposed system was also found to outperform human experts in classification accuracy.

Motor imagery(MI)-based Brain-Computer Interfaces (BCI) have shown increased potential for the rehabilitation of stroke patients; nonetheless, their implementation in clinical practice has been restricted due to their low accuracy performance. To date, although a lot of research has been made in benchmarking and highlighting the most valuable classification algorithms in BCI configurations, most of them are using offline data and not from real BCI performance during the closed-loop (or online) sessions. Since rehabilitation training relies on the availability of an accurate feedback system, we surveyed articles of current and past EEG-based BCI frameworks who report the online classification of the movement of two upper limbs in both healthy volunteers and stroke patients. We found that the recently developed Deep Learning methods do not outperform the traditional machine learning algorithms. In addition, patients and healthy subjects exhibit similar classification accuracy in current BCI configurations. Lastly, in terms of neurofeedback modality, Functional Electrical Stimulation (FES) yielded the best performance compared to non-FES systems.

Deep learning dominates automated animal activity recognition (AAR) tasks due to the high performance on large-scale datasets. However, constructing centralised data across diverse farms raises data privacy issues. Federated learning (FL) provides a distributed learning solution to train a shared model by coordinating multiple farms (clients) without sharing their private data. Whereas directly applying FL to AAR tasks often faces two challenges: client-drift during local training and gradient conflicts during global aggregation. In this study, we develop a novel FL framework called FedAAR to achieve AAR with sensor data. Specifically, we devise a prototype-guided local update module to alleviate the client-drift issue, which introduces global prototypes as shared knowledge to force clients to learn consistent features. To reduce gradient conflicts between clients, we design a gradient refinement-based aggregation module to eliminate conflicting components between client gradients during global aggregation, thereby improving the agreement between clients. Experiments are conducted on a public dataset to verify FedAAR’s effectiveness, which consists of 87,621 2-s motion data. The results demonstrate that FedAAR outperforms state-of-the-arts, with precision (75.23%), recall (75.17%), F1-score (74.70%), and accuracy (88.88%), respectively. The ablation experiments also show FedAAR’s robustness against various factors (i.e., different data sizes, communication frequency, and client numbers).

An electrocardiograph (ECG) reflects the health of the human heart and is used to help diagnose arrhythmia and myocardial infarction(MI) in clinical practice. Early diagnosis of arrhythmia helps implement preventive measures and plays a crucial role in saving a patient's life. With the increasing demand of clinicians for ECG analysis technology, intelligent detection and diagnosis of ECG signals has become a more efficient means to assist physicians in diagnosing cardiovascular diseases. This paper introduces an ECG diagnosis approach based on an ensemble deep learning combination of CNN(convolutional neural network) and SLAP(stacked-long short term memory architecture for prediction) architecture. ECG data is denoised and further divided into single heartbeats to achieve data standardization and sample diversity. Adam optimizer and BCEwithlogitsloss multi-classification loss function were used to enhance the model effect, and the system achieved the classification effect of 99.3% average accuracy, 99.0% F1-value, and 99.2% sensitivity in MIT-BIH standard database classification. It also shows good generalization ability on the Tianchi data set.

Over recent years, the importance of patent literature has become more recognized in the academic setting. In the context of artificial intelligence, deep learning, and data sciences, patents are relevant to not only industry but also academe and other communities. In this article, we focus on deep tomographic imaging and perform a preliminary landscape analysis of the related patent literature. Our search tool is PatSeer . Our patent bibliometric data is summarized in various figures and tables. In particular, we qualitatively analyze key deep tomographic patent literature.

Deep learning techniques are increasingly being recognized as effective image classifiers. Aside from their successful performance in past studies, the accuracies have varied in complex environments in comparison with the popularly applied machine learning classifiers. This study seeks to explore the feasibility for using a U-Net deep learning architecture to classify bi-temporal high resolution county scale aerial images to determine the spatial extent and changes of land cover classes that directly or indirectly impact tidal marsh. The image set used in the analysis is a collection of a 1-m resolution collection of National Agriculture Imagery Program (NAIP) tiles from 2009 and 2019 covering Beaufort County, South Carolina. The U-net CNN classification results were compared with two machine learning classifiers, the Random Trees (RT) and the Support Vector Machine (SVM). The results revealed a significant accuracy advantage in using the U-Net classifier (92.4%) as opposed to the SVM (81.6%) and RT (75.7%) classifiers for overall accuracy. From the perspective of a GIS analyst or coastal manager, the U-Net classifier is now an easily accessible nad powerful tool for mapping large areas. Change detection analysis indicated little areal change on marsh extent, though increased land development throughout the county has the potential to negatively impact the health of the marshes. Future work should explore applying the constructed U-Net classifier to coastal environments in large geographic areas, while also implementing other data sources (e.g., LIDAR, multispectral data) to enhance classification accuracy.

Phenotypes are driven by regulated gene expression, which in turn are mediated by complex interactions between diverse biological molecules. Protein-DNA interactions such as histone and transcription factor binding are well studied, along with RNA-RNA interactions in short RNA silencing of genes. In contrast, lncRNA-protein interaction (LPI) mechanisms are comparatively unknown, likely driven by the difficulties in studying LPI. However, LPI are emerging as key interactions in epigenetic mechanism, playing a role in development and disease. Their importance is further highlighted by their conservation across kingdoms. Hence, interest in LPI research is increasing. We therefore review the current state of the art in lncRNA-protein interactions. We specifically surveyed recent computational methods and databases which researchers can exploit for LPI investigation. We discovered that algorithm development is heavily reliant on a few generic databases containing curated LPI information. We show that early methods predict LPI using molecular docking, have limited scope and are slow, creating a data processing bottleneck. Recently, machine learning has become the strategy of choice in LPI prediction, likely due to the rapid growth in machine learning infrastructure and expertise. While many of these methods have notable limitations, machine learning is expected to be the basis of modern LPI prediction algorithms.

The use of active methodologies in the university is a priority to achieve higher quality learning. One of these methodologies with the greatest potential for training in competencies is Project-Oriented Learning (PLA), using it in an innovative way. Associating the use of this methodology with the objectives of sustainable development, which have become even more important since the Pandemic by COVID-19, can be a good idea to achieve a more sustained and situated learning. The aim of this study is to find out to what extent research on teaching innovation with Project-Oriented Learning is associated with the Sustainable Development Goals. A systematic review was carried out as indicated by PRISMA through the following databases: WOS and Scopus. WOS found 15 articles on AoP and 6 on Project-Oriented Learning and sustainability. In Scopus 2 were found in 2019. The main results show that in the University, especially in the branches of engineering, AoP is widely used, however, it is rarely related to SDGs. Among the conclusions, we highlight the need for research on project-oriented learning and sustainable development goals.

CNN-based methods have dominated the field of aerial scene classification for the past few years. While achieving remarkable success, CNN-based methods suffer from excessive parameters and notoriously rely on large amounts of training data. In this work, we introduce few-shot learning to the aerial scene classification problem. Few-shot learning aims to learn a model on base-set that can quickly adapt to unseen categories in novel-set, using only a few labeled samples. To this end, we proposed a meta-learning method for few-shot classification of aerial scene images. First, we train a feature extractor on all base categories to learn a representation of inputs. Then in the meta-training stage, the classifier is optimized in the metric space by cosine distance with a learnable scale parameter. At last, in the meta-testing stage, the query sample in the unseen category is predicted by the adapted classifier given a few support samples. We conduct extensive experiments on two challenging datasets: NWPU-RESISC45 and RSD46-WHU. The experimental results show that our method yields state-of-the-art performance. Furthermore, several ablation experiments are conducted to investigate the effects of dataset scale, the impact of different metrics and the number of support shots; the experiment results confirm that our model is specifically effective in few-shot settings.

Creative thinking is increasingly recognised as an essential ability that should be part of school curricula. Given the move towards online learning and assessment, we investigate whether mathematical creativity can be assessed at-scale in the Numbers game, an arithmetic game in Math Garden, a popular online math practice platform. In the Numbers game, a generalisation of the 24 Game, children are asked to figure out how to compute a target number using basic arithmetic operations and a given set of numbers. We argue that creative thinking is required when the search space is complex, and propose that the base-pattern, i.e., the sequence of the operations needed to solve a Numbers game item, indicates search space complexity. We then demonstrate that items with disordered base-patterns are more likely to require mathematical creativity to figure out. Specifically, our analysis shows that for items with only one solution sequence, those with disordered base-patterns are more difficult and take longer to solve compared to items with ordered base-patterns. For items where multiple solution sequences are possible, nine times out of ten children choose ordered over disordered base-patterns. We conclude that the Numbers game has potential for assessing mathematical creativity at-scale.

In recent years, team-based learning (TBL) is gaining popularity as a student-centered active collaborative learning strategy in healthcare education. This paper reports the design, implementation, and impact of a "hybrid team-based learning" (H-TBL) for one respiratory lecture in year two undergraduate physiotherapy program in 2019. A retrospective study was conducted, including 136 second-year undergraduate physiotherapy students using H-TBL design for one respiratory lecture topic. Student engagement was evaluated based on the percentage of completion for pre-class work, attendance to classroom session, and submission of formative creative assignment. Student' performance on formative creative tasks was evaluated based on thinking and learning rubric. Student perceptions were assessed based on the student's feedback using "Mentimeter." 109/ 136 (80%) students attended the COPD 2 session. 90/109 (82%) students engaged in COPD 1 (web-based) and tRAT in COPD 2 session. 54/109 (50%) students provided feedback and 67/90 (74%) students submitted formal formative creative assignment on completion of COPD 2 session. This study confirms that H-TBL enhances student's active engagement, creativity, and equilibration of their subject knowledge. Future randomized studies are mandated to explore the validity and specificity of H-TBL in diverse physiotherapy curriculum to evaluate the long-term student engagement and academic performance.

Adaptive bitrate (ABR) algorithms optimize the quality of streaming experiences for users in client-side video players especially in unreliable or slow mobile networks. Several rule-based heuristic algorithms can achieve stable performance, but they sometimes fail to adapt properly to changing network conditions. Fluctuating bandwidth may cause algorithms to default to behavior that creates a negative experience for the user. ABR algorithms can be generated with reinforcement learning, a decision-making paradigm in which an agent learns to make optimal choices through interactions with an environment. Training reinforcement learning algorithms for bitrate streaming requires building a simulator for an agent to experience interactions quickly; training an agent in the real environment is infeasible due to the long step times in real environments. This project explores using supervised learning to construct a world-model, or a learned simulator, from recorded interactions. A reinforcement learning agent trained inside of the learned model, rather than a simulator, can outperform rule-based heuristics. Furthermore, agents trained inside the learned world-model can outperform model-free agents in low sample regimes. This work highlights the potential for world-models to quickly learn simulators, and to be used to generate optimal policies.

Prediction of stock groups values has always been attractive and challenging for shareholders. This paper concentrates on the future prediction of stock market groups. Four groups named diversified financials, petroleum, non-metallic minerals and basic metals from Tehran stock exchange are chosen for experimental evaluations. Data are collected for the groups based on ten years of historical records. The values predictions are created for 1, 2, 5, 10, 15, 20 and 30 days in advance. The machine learning algorithms utilized for prediction of future values of stock market groups. We employed Decision Tree, Bagging, Random Forest, Adaptive Boosting (Adaboost), Gradient Boosting and eXtreme Gradient Boosting (XGBoost), and Artificial neural network (ANN), Recurrent Neural Network (RNN) and Long short-term memory (LSTM). Ten technical indicators are selected as the inputs into each of the prediction models. Finally, the result of predictions is presented for each technique based on three metrics. Among all algorithms used in this paper, LSTM shows more accurate results with the highest model fitting ability. Also, for tree_based models, there is often an intense competition between Adaboost, Gradient Boosting and XGBoost.

Educational data-mining is an evolving discipline that focuses on the improvement of self-learning and adaptive methods. It is used for finding hidden patterns or intrinsic structures of educational data. In the arena of education, the heterogeneous data is involved and continuously growing in the paradigm of big-data. To extract meaningful information adaptively from big educational data, some specific data mining techniques are needed. This paper presents a clustering approach to partition students into different groups or clusters based on their learning behavior. Furthermore, personalized e-learning system architecture is also presented which detects and responds teaching contents according to the students’ learning capabilities. The primary objective includes the discovery of optimal settings, in which learners can improve their learning capabilities. Moreover, the administration can find essential hidden patterns to bring the effective reforms in the existing system. The clustering methods K-Means, K-Medoids, Density-based Spatial Clustering of Applications with Noise, Agglomerative Hierarchical Cluster Tree and Clustering by Fast Search and Finding of Density Peaks via Heat Diffusion (CFSFDP-HD) are analyzed using educational data mining. It is observed that more robust results can be achieved by the replacement of existing methods with CFSFDP-HD. The data mining techniques are equally effective to analyze the big data to make education systems vigorous.

Developing efficient Artificial Intelligence (AI)-enabled system to substitute human role in non-destructive testing is an emerging topic of considerable interest. In this study, we propose a novel impact-echo analysis system using online machine learning, which aims at achieving near-human performance for assessment of concrete structures. Current computerized impact-echo systems commonly employ lab-scale data to validate the models. In practice, however, the echo patterns can be far more complicated due to varying geometric shapes and materials of structures. To deal with a large variety of unseen data, we propose a sequential treatment for echo characterization. More specifically, the proposed system can adaptively update itself to approaching human performance in impact-echo data interpretation. To this end, a two-stage framework has been introduced, including echo feature extraction and the model updating scheme. Various state-of-the-art online learning algorithms have been reviewed and evaluated for the task. To conduct experimental validation, we collected 10,940 echo instances from multiple inspection sites with each sample had been annotated by human experts with healthy/defective condition labels. The results demonstrated that the proposed scheme achieved favorable echo pattern classification accuracy with high efficiency and low computation load.

This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.

Despite UAV multi-target detection exhibits considerable developmental potential worldwide, it suffers distinct challenges compared with traditional tasks in this field. These challenges include insufficient feature extraction capabilities for small targets, limited capabilities for multi-dimensional feature fusion, as well as constraints on hardware computation parameters. Especially in mission scenarios such as disaster detection, these challenges will be further amplified. Consequently, this paper introduces SSE-YOLO, an innovative YOLO framework algorithm specially designed to address these challenges. To enhance the model's feature extraction capability, we employ the SPDConv module to replace the original Conv in the backbone section, utilizing depth-separable convolution instead of traditional convolution pooling. Concurrently, we eliminate the SPPF module at the bottom and address a new Separate Kernel Attention Pyramid Pooling (SKAPP) module, substantially enhancing the feature fusion capability at the model's core. Moreover, to address the challenge of multi-dimensional feature fusion, we replace the Concat module of the neck and head with E-BiFPN, transmitting feature information from the backbone to the lower network through four CBS blocks, which effectively resolves the issue of lost contextual information in the model. Meanwhile, SSE-YOLO undergoes ablation experiments on the VisDrone2019 dataset to evaluate its effectiveness against alternative methods, and experimental results illustrate the model's exceptional precision in detecting UAV targets. In comparison to models with comparable experimental accuracy, SSE-YOLO requires remarkably fewer parameters. On the VisDrone2019-DET-test-dev dataset, SSE-YOLO enhances mAP by 17.3%, with a 42.5% reduction in the parameter amounts. Therefore, the proposed method effectively tackles the challenge of reconciling low parameters and high accuracy, presenting a novel pathway for deep learning-based UAV multi-target detection.

A pandemic can have a huge impact on normal human life and the economy, taking COVID-19 as an example. While the population flow between countries and regions is the main factor affecting the change of a pandemic, exactly as the airline network. Therefore, realizing the overall control of airports is an effective way to control a pandemic. However, restricted to the differences in prevention and control policies in different areas and privacy issues, the patients’ personal data of the medical center cannot be effectively combined with the passengers’ personal data. This prevents more precise airport control decisions from being made. To the end, this paper designs a novel data sharing framework (i.e., PPChain) based on blockchain and federated learning. The experiment shows that the relationship between the epidemic and aircraft transport can be effectively explored by PPChain, without sharing raw data. This approach does not require centralized trust and improves the security of the shareing process.The scheme can help formulate more scientific and rational prevention and control policies on airports’ control. And it can use aerial data to predict pandemics more accurately.

Machine learning plays a key role in present day crime detection, analysis and prediction. The goal of this work is to propose methods for predicting crimes classified into different categories of severity. We implemented visualization and analysis of crime data statistics in recent years in the city of Boston. We then carried out a comparative study between two supervised learning algorithms, which are decision tree and random forest based on the accuracy and processing time of the models to make predictions using geographical and temporal information provided by splitting the data into training and test sets. The result shows that random forest as expected gives a better result by 1.54% more accuracy in comparison to decision tree, although this comes at a cost of at least 4.37 times the time consumed in processing. The study opens doors to application of similar supervised methods in crime data analytics and other fields of data science

In this paper, we tackle air quality forecasting by using machine learning approaches to predict the hourly concentration of air pollutants (e.g., Ozone, PM_2.5 and Sulfur Dioxide). Machine learning, as one of the most popular techniques, is able to efficiently train a model on big data by using large-scale optimization algorithms. Although there exists some works applying machine learning to air quality prediction, most of the prior studies are restricted to small scale data and simply train standard regression models (linear or non-linear) to predict the hourly air pollution concentration. In this work, we propose refined models to predict the hourly air pollution concentration based on meteorological data of previous days by formulating the prediction of 24 hours as a multi-task learning problem. It enables us to select a good model with different regularization techniques. We propose a useful regularization by enforcing the prediction models of consecutive hours to be close to each other, and compare with several typical regularizations for multi-task learning including standard Frobenius norm regularization, nuclear norm regularization, ℓ_2,1 norm regularization. Our experiments show the proposed formulations and regularization achieve better performance than existing standard regression models and existing regularizations.

The fast-paced advancements in the technological space and its application have influenced greatly its usage in teaching especially in science and mathematics subjects. The overall objective of this study was to examine the physical proximity of learning in shaping students’ mastery of technology-enhanced mathematics and science concepts. Consequently, the study investigates how technology can promote teaching presence toward the mastery of mathematics and science concepts and how the latter can be grasped by the learners using physical proximity strategies. This research study used a mixed-method research design and was conducted in Kayonza District (Eastern Province) and Gasabo District (Kigali), Rwanda. The participants were postgraduate students at the University of Rwanda, College of Education undertaking a master degree in chemistry education, mathematics education, physics education and biology education under the Africa Centre of Excellence for Innovative Teaching and Learning Mathematics and Science. A sample size of 88 students was selected from both Remera and Rukara campuses. Participants were in a range of 21-40 years old. The study used both interviews and questionnaires to collect empirical data. Qualitative data was analyzed using thematic analysis while quantitative data was analyzed using R software. The study reveals that a virtual lab is a vital tool in promoting teaching presence regarding the mastery of mathematics and science concepts. The use of virtual labs seems to foster instructional design and organization from teachers. Moreover, virtual labs seem to facilitate meaningful discourses, interactions between learners and between the learners and the teacher. The findings show also that virtual visualizing seems also to play a role in direct instruction where the teacher offers guidance and direction to learners on various subjects or issues of contention that may need the clarity. Thus 87.6% of the respondents affirm that technology integration in learning is efficient in bridging the gap of physical proximity among learners and teachers through various virtual instruments and platforms. The study also demonstrates that various forms of technology that can be used to bring mathematics and science concepts to the learners’ physical proximity including WhatsApp, Microsoft Teams, Google Meet, Zoom and Webex. The study therefore recommends that visualization should be integrated in the curricula, training of teachers and students to maximize physical proximity components and sharing of best practices among teachers and students.

Children’s learning of place value is critical to their future study of mathematics. However, its learning presents a huge challenge for many learners. As result they develop misconceptions and thencommit errors that become an encumbrance to their understanding of place value. It is therefore important to identify these misconceptions and their associated errors early and help children to overcome them. This article reports the findings from literature on what misconceptions learners display in the learning of place value and how they can best be supported to overcome them. The results show that despite the importance of this topic there are limited studies devoted to its research. The dearth of these studies creates a gap in the study of place value.

This paper focuses on the new users cold-start issue in the context of recommender systems. New users who do not receive pertinent recommendations may abandon the system. In order to cope with this issue, we use active learning techniques. These methods engage the new users to interact with the system by presenting them with a questionnaire that aim to understand their preferences to the related items. Example of questions may include "do you like this book?" and the users answer,"yes", "no", "I have not read it (unknown)", will reflect the degree of interest for the item by the users. As a consequence, the system can learn the users' preferences from these answers. The goal of active learning is to correctly choose the questions (items) for users. Thus it is necessary to personalize the questionnaires to retrieve the maximum information by avoiding "unknown" answers. In this paper, we propose an active learning technique that exploits past users' interests and past users' predictions in order to identify the best questions to ask.

Negative mental health in students currently is classified as a global crisis with the highest and lowest student achievers recognized at greatest risk. Public schooling, in reproducing accepted psychosocial beliefs through standardized learning, developed separately from necessitating student mental health, in contrast to self-directed learning. Differing from standardized learning, the objective of self-directed learning in public schools is the creation of relevant support structures for student mental health, promoting positive psychosocial outcomes. The designed separation of public schooling from both mental health and self-directed learning was first acknowledged—and lamented—by John Dewey, over 100 years ago, in anticipating today’s mental health crisis. Yet, in responding effectively to the limitations of COVID-19, self-directed learning became an acknowledged learning method in public schools, potentially able to be accommodated by them regularly in support of mental health through the use of online technology. This study investigates the COVID-19 results of self-directed online learning in public schools through a Google Scholar search of peer reviewed research regarding self-directed learning, online learning, and mental health during COVID-19, recommending support for self-initiated self-directed online learning so that self-directed learning can continue, post COVID-19, improving student mental health in public schools, leading to positive psychosocial outcomes.

This paper presents a novel approach for accurate counting and localization of tropical plants in aerial images that is able to work in new visual domains in which the available data is not labeled. Our approach uses deep learning and domain adaptation, designed to handle domain shift between the training and test data, which is a common challenge in this agricultural applications. This method uses a source dataset with annotated plants and a target dataset without annotations, and adapts a model trained on the source dataset to the target dataset using unsupervised domain alignment and pseudolabeling. The experimental results show the effectiveness of this approach for plant counting in aerial images of pineapples under significative domain shift, achieving a reduction up to 97% in the counting error when compared to the supervised baseline.

Background: Ensemble tree-based models such as Xgboost are highly prognostic in cardiovascular medicine, as measured by the Clinical Effectiveness Metric (CEM). However, their ability to handle correlated data, such as hospital-level effects, are limited. Objectives: The aim of this work is to develop a binary outcome mixed effects Xgboost (BME) model that integrates random effects at the hospital level. To ascertain how well the model handles correlated data in cardiovascular outcomes, we aims to assess its performance and compare it to fixed effects Xgboost and traditional logistic regression models. Methods: A total of 227,087 patients over 17 years of age, undergoing cardiac surgery from 42 UK hospitals between 1 Jan 2012 and 31 Mar 2019 were included. The dataset was split into two cohorts: Training/Validation (n = 157196; 2012-2016) and Holdout (n = 69891; 2017-2019). The outcome variable was 30 days mortality with hospitals considered as clustering variable. The logistic regression, mixed effects logistic regression, Xgboost and binary outcome mixed effects Xgboost (BME) were fitted to both standardized and unstandardized datasets across a range of sample sizes and the estimated prediction power metrics were compared to identify the best approach. Results: The exploratory study found high variability in hospital-related mortality across datasets, which supported the adoption of mixed effects models. Unstandardized Xgboost BME demonstrated marked improvements in predictor power over the Xgboost model at small sample size ranges, but performance differences decreased as dataset sizes increased. Generalized linear models (glm) and generalized linear mixed-effects models (glmer) models followed similar results, with Xgboost models excelling also at greater sample sizes. Conclusions: These findings suggest that integrating mixed effects into machine learning models can enhance their applicability in clinical settings where sample size is small such as rare conditions.

The aim of this paper is to contribute to the body of knowledge about Project-Based Learning (PBL) methodology in higher education by describing and analysing interrelations between competencies, and their contribution to knowledge transfer (KT) and students’ rating of the project. The sample consisted of 464 students from the Universities of Huelva (N=347; 74.8%) and Murcia (N= 117; 25.2%), enrolled in the second year of a degree in either Infant or Primary Education. Data was collected through a self-administered questionnaire comprising a total of 53 items measuring General, Specific and Transversal competencies, as well as students’ rating of the project. Competencies were selected from the course programmes for the degrees in Infant and Primary Education. Preliminary results showed that competencies were moderately to highly acquired after PBL, and that students reported notable KT as well as a positive assessment of the project. KT showed a high degree of association with students’ ratings and was established as a key factor in learning and learner satisfaction in higher education.

Water quality control employs techniques mostly targeting individual analytes; group detection is also practiced, but the choice of group methods is limited, which supports interest in developing such methods. We have examined an interaction of hypochlorite with a chlorine-containing heptamethine carbocyanine dye in the presence of 30 organic and inorganic model analytes that were found to induce diverse color changes in the system. The main supposed mechanisms are retardation of the dye oxidation with hypochlorite (presumably by scavenging chlorine radicals) and substitution of chlorine atom in the dye by the most nucleophilic analytes (amines, amino acids, proteins, DNA, phenol). The grass-green substitution product is more contrastingly visible against the dark-purple hypochlorite oxidation product of the dye than against the original emerald-green dye. The indicator reaction is monitored photographically for 10–40 min and the images are processed using principal component analysis (PCA) or linear discriminant analysis (LDA), allowing for data convolution for the complex color transitions. Nitrogen compounds are discriminated from the others, and more reactive analytes (tryptophan, cysteine, bovine serum albumin, and DNA) are detected in the presence of less reactive ones in natural water. The system is promising for the development of group assays for dissolved organic matter and discrimination of water samples.

This work presents a methodology for the generation and classification of phase resolved partial discharges (PRPD) patterns based on the use of a printed UHF monopole antenna and signal con-ditioning circuit to reduce hardware requirements. For this purpose, envelope detection technique was applied. In addition, test objects such as a hydrogenerator bar, dielectric disks with internal cavities in an oil cell, potential transformer, and tip-tip electrodes immersed in oil were used to generate partial discharge (PD) signals. To detect and classify partial discharges, the standard IEC 60270 (2000) method was used as reference. After acquisition of conditioned UHF signals, digital signal filtering threshold technique was used, and peaks of partial discharges envelopes pulses were extracted. Feature selection techniques were used to classify the discharges and choose the best features to train machine learning algorithms, such as multilayer perceptron, support vector ma-chine and decision tree. Accuracies greater than 84% were met, revealing the classification potential of the methodology proposed in this work.

ABSTRACT Background It is important to be able to predict, for each individual patient, the likelihood of later metastatic occurrence, because the prediction can guide treatment plans tailored to a specific patient to prevent metastasis and to help avoid under- or over-treatment. Deep Neural Network (DNN) learning, commonly referred to as deep learning, has become popular due to its success in image detection and prediction, but questions such as whether deep learning outperforms other machine learning methods when using non-image clinical data remain unanswered. Grid search has been introduced to deep learning hyperparameter tunning for the purpose of improving its prediction performance, but the effect of grid search on other machine learning methods are under-studied. In this research, we take the empirical approach to study the performance of deep learning and other machine learning methods when using non-image clinical data to predict the occurrence of breast cancer metastasis (BCM) 5, 10, or 15-years after the initial treatment. We developed DNN models as well as models using 9 other machine learning methods including Naive Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), LASSO, Decision Tree (DT), k-Nearest Neighbors (KNN), Random Forrest (RF), AdaBoost (ADB), and XGBoost (XGB). We used grid search to tune hyperparameters for all methods. We then compared the deep learning models to the models trained using the 9 other machine learning methods. Results Based on the mean test AUC results, DNN ranks 6th, 4th, and 3rd when predicting 5-year, 10-year, and 15-year BCM respectively, out of 10 machine learning methods. The top performing methods in predicting 5-year BCM are XGB(1^st), RF(2^nd), and KNN(3^rd). For predicting 10-year BCM the top performers are XGB (1^st), RF(2^nd), and NB(3^rd) . Finally, for 15-year BCM the top performers are SVM (1^st), LR and LASSO (tied for 2^nd), and DNN (3^rd). The ensemble methods RF and XGB outperform other methods when data are less balanced, while SVM, LR, LASSO, and DNN outperform other methods when data are more balanced. Our statistical testing results show that at a significance level of 0.05 DNN overall performs no worse than other machine learning methods when predicting 5-year, 10-year, and 15-year BCM. Conclusions Our results show that deep learning with grid search overall performs at least as well as other machine learning methods when using non-image clinical data. It is interesting to note that some of the other machine learning methods such as XGB, RF, and SVM are very strong competitors of DNN when incorporating grid search. It is also worth noting that the computation time required to do grid search with DNN is way more than that required to do grid search with the other 9 machine learning methods.

The convergence of Class Incremental Learning (CIL) and Machine Unlearning (MU) is a rapidly developing field in machine learning, especially relevant in adaptive and privacy-sensitive environments like finance. CIL enables models to learn new data classes over time without losing previously acquired knowledge, while MU focuses on selectively forgetting specific data to comply with privacy laws or mitigate security risks. In this paper, we examine the theoretical foundations and practical applications of both approaches, particularly in the financial domain. We explore how these two paradigms interact and complement each other, discuss key algorithms, and present examples to illustrate their applications in areas such as portfolio management, fraud detection, and data privacy. Finally, we explore challenges and potential future directions in achieving optimal synergy between CIL and MU.

This paper examines the utility and exploitation of non-obvious "alien" AI constructions, artificial intelligence solutions that significantly deviate from human intuition and traditional problem-solving approaches. It explores recent revelations, key characteristics, applications across various domains, and far-reaching implications for scientific research and innovation. Particular attention is given to developments in mathematical reasoning, drug discovery, and healthcare. The paper also discusses challenges in implementation, ethical considerations, and future directions, including meta-learning algorithms and human-AI collaboration frameworks. By synthesizing current research and identifying emerging trends, this paper aims to provide a basic understanding of the transformative potential of non-obvious AI solutions in reshaping scientific discovery and biomedical innovation.

Without the use of medicine drones, users are responsible for transporting goods at a high cost. The goal of this patient monitoring system is to identify people's health and, if necessary, administer medicine. The transportation drone is capable of finding healthcare information in a 360-degree rotation within the transportation infrastructure. IoT: Drone doctors are critical for the transportation of small gadgets such as drug treatments, blood leakages, and vaccines in the critical conditions of a heart patient, in the event of failure of traffic location infrastructure, highway roads, or hospitals due to intense climate or site visitor congestion, and for the transportation of small gadgets such as drug treatments, blood leakages, and vaccines. When transmission is difficult, the self-maintaining drone is the format for quickly transporting drug treatments to the appropriate locations. The shipping drone equipped with an Ardupilot can drive in autopilot mode, which guides the drone to its destination. It has a 7-minute flying period and can deliver up to 2 kg of medicine. When the detected heartbeat is 94bpm and the fever range is 101 degrees, a method has been presented in which an IoT Drone Doctor (IDD) System distributes the first AID box to vulnerable patients and heart patients.

Facial expressions play a key role in interpersonal communication when it comes to negotiating our emotions and intentions, as well as interpreting those of others. Research has shown that we can connect to other people better when we exhibit signs of empathy and facial mimicry. However, the relationship between empathy and facial mimicry is still debated. Among the factors contributing to the difference in results across existing studies is the use of different instruments for measuring both empathy and facial mimicry, as well as often ignoring the differences across various demographic groups. This study first looks at the differences in empathetic abilities of people across different demographic groups based on gender, ethnicity and age. The empathetic ability is measured based on the Empathy Quotient capturing a balanced representation of both emotional and cognitive empathy. Using statistical and machine learning methods, the study then investigates the correlation between the empathetic ability and facial mimicry of subjects in response to images portraying different emotions displayed on a computer screen. Unlike the existing studies measuring facial mimicry using electromyography, this study employs a technology detecting facial expressions based on video capture and deep learning. This choice was made in the context of increased online communication during and post the COVID-19 pandemic. The results of this study confirm the previously reported difference in the empathetic ability between females and males. However, no significant difference in the empathetic ability was found across different age and ethnic groups. Furthermore, no strong correlation was found between empathy and facial reactions to faces portraying different emotions shown on a computer screen. Overall, the results of this study can be used to inform the design of online communication technologies and tools for training empathy team leaders, educators, social, and health care providers.

Making computing machines mimic living organisms has captured the imagination of many since the dawn of digital computers. However, today’s artificial intelligence technologies fall short in replicating even the basic autopoietic and cognitive behaviors found in primitive biological systems. According Charles Darwin, the difference in mind between humans and the higher animals, great as it is, certainly is one of degree and not of kind. Autopoiesis refers to the behavior of a system that replicates itself and maintains its own identity and stability while facing fluctuations caused by external influences. Cognitive behaviors model the system’s state, sense internal and external changes, analyze, predict and take action to mitigate any risk to its functional fulfilment. How did intelligence evolve? what is the relationship between the mind and body? Answers to these questions should guide us to infuse autopoietic and cognitive behaviors into digital machines. In this paper we use recent advances in our understanding of general theory of information, and the role of structures in managing the transformations between information and knowledge to pave the path to infuse autopoietic and cognitive functions into digital computing and build a new class of intelligent machines going beyond the current state of the art.

The ability to read and quantify nucleic acids such as DNA and RNA using sequencing technologies has revolutionized our understanding of life. With the emergence of synthetic biology, these tools are now being put to work in new ways - enabling de novo biological design. Here, we show how sequencing is supporting the creation of a new wave of biological parts and systems, as well as providing the vast data sets needed for the machine learning of design rules for predictive bioengineering. However, we believe this is only the tip of the iceberg and end by providing an outlook on recent advances that will likely broaden the role of sequencing in synthetic biology and its deployment in real-world environments.

Organised hiking and trekking tours are promoted by many providers in adventure travel. Such guided tours shall be engaging for the tourists and evoke positive attitudes towards enjoying nature. We present the Trekking Engagement Profile as a tool to evaluate engagement factors of such guided tours, based on engagement research performed in a different domain, namely evaluating engagement in museums and science centres. This tool shall strengthen guides’ soft skills and enable them to increase engagement during an ongoing arrangement. For instance, the Trekking Engagement Profile can be applied when tourists indicate that the quality of a guided tour is not entirely to their liking. We show the viability of using the Trekking Engagement Profile in a small study with guides and participants of trekking tours offered by the Norwegian Trekking Association. Further, we offer guidance and charts to promote its practical use.

Viral infections cause metabolic dysregulation in the infected organism. The present study used metabolomics techniques and machine learning algorithms to retrospectively analyze the alter-ations of a broad panel of metabolites in the serum and urine of a cohort of 126 patients hospi-talized with COVID-19. Results were compared with those of 50 healthy subjects and 45 COVID-19 negative patients but with bacterial infectious diseases. Metabolites were analyzed by gas chro-matography coupled to quadrupole time-of-flight mass spectrometry. The main metabolites al-tered in the sera of COVID-19 patients were those of pentose glucuronate interconversion, ascorbate and fructose metabolism, nucleotide sugars, and nucleotide and amino acid metabolism. Alterations in serum maltose, mannonic acid, xylitol, or glyceric acid metabolites segregated positive patients from the control group with high diagnostic accuracy, while succinic acid seg-regated positive patients from those with other disparate infectious diseases. Increased lauric acid concentrations were associated with severity of infection and death. Urine analyses could not discriminate between groups. Targeted metabolomics and machine learning algorithms facilitated the exploration of the metabolic alterations underlying COVID-19 infection, and to identify po-tential biomarkers for the diagnosis and prognosis of the disease.

The coronaviral pandemic has led to a shift in traditional teaching methods to more innovative approaches, such as high-fidelity patient simulation (HFPS), which can improve students’ clinical judgement and decision-making for quality patient care. A modified guideline was introduced to enhance students’ satisfaction and self-confidence in learning through HFPS. The study involved 189 baccalaureate nursing students, with 92 in the intervention group and 97 in the control group. The intervention group received the modified HFPS guideline, while the control group received standard treatment with basic instruction. After the HFPS debriefing session, students provided narrative feedback on their learning experience. The quantitative results showed that students in the intervention group reported a significant improvement in satisfaction and self-confidence in learning compared to the control group. The modified HFPS guideline provided clear guidance for students to learn and apply knowledge and skills more effectively, leading to increased engagement during interactive simulation sessions. The results suggest that the HFPS guideline should be added to the curriculum to enhance students’ satisfaction and self-confidence in learning, even in junior students. Innovative teaching methods, such as HFPS, can be necessary and beneficial for healthcare professional training, after the pandemic.

Background: the primary care service in Catalonia has operated an asynchronous teleconsulting service between GPs and patients since 2015 (eConsulta), which has generated some 500,000 messages. New developments in big data analysis tools, particularly those involving natural language, can be used to accurately and systematically evaluate the impact of the service. Objective: the study was intended to examine the predictive potential of eConsulta messages through different combinations of vector representation of text and machine learning algorithms and to evaluate their performance. Methodology: 20 machine learning algorithms (based on 5 types of algorithms and 4 text representation techniques)were trained using a sample of 3,559 messages (169,102 words) corresponding to 2,268 teleconsultations (1.57 messages per teleconsultation) in order to predict the three variables of interest (avoiding the need for a face-to-face visit, increased demand and type of use of the teleconsultation). The performance of the various combinations was measured in terms of precision, sensitivity, F-value and the ROC curve. Results: the best-trained algorithms are generally effective, proving themselves to be more robust when approximating the two binary variables "avoiding the need of a face-to-face visit" and "increased demand" (precision = 0.98 and 0.97, respectively) rather than the variable "type of query"(precision = 0.48). Conclusion: to the best of our knowledge, this study is the first to investigate a machine learning strategy for text classification using primary care teleconsultation datasets. The study illustrates the possible capacities of text analysis using artificial intelligence. The development of a robust text classification tool could be feasible by validating it with more data, making it potentially more useful for decision support for health professionals.

Deep learning has increasingly been employed to identify minerals. However, deep learning can only be used to identify minerals in the distribution of the training set, while any mineral outside the spectrum of the training set is inevitably categorized erroneously within a predetermined class from the training set. To solve this problem, the study introduces the approach that amalgamates One-Class Support Vector Machines (OCSVM) with the ResNet architecture for the out-of-distribution mineral detection. Initially, ResNet undergoes training using a training set comprising well-defined minerals. Subsequently, the earlier layers of the trained ResNet are employed to extract the discriminative features of the mineral under consideration. These extracted mineral features then become the input for OCSVM. When OCSVM discerns the mineral in the training set's distribution, it triggers the subsequent layers within the trained ResNet, facilitating the accurate classification of the mineral into one of the predefined categories encompassing the known minerals. In the event OCSVM identifies the mineral out of the training set's distribution, it is unequivocally categorized as an unclassified or 'unknown' mineral. Empirical results substantiate the method's capability to identify out-of-distribution minerals while concurrently maintaining a commendably high accuracy rate for the classification of the 36 in-distribution minerals.

With the development of remote sensing satellite technology for Earth observation, remote sensing stereo images have been used for three-dimensional reconstruction in various fields, such as urban planning and construction. However, remote sensing images often include noise, occluded regions, weakly textured areas and repeated textures, which can lead to reduced accuracy in stereo matching and affect the quality of the 3D reconstruction results. To reduce the impact of complex scenes in remote sensing images on stereo matching and to ensure both speed and accuracy, we propose a new end-to-end stereo matching network based on convolutional neural networks (CNNs). The proposed stereo matching network can learn features at different scales from the original images and construct cost volumes with varying scales to obtain richer scale information. Additionally, when constructing the cost volume, we introduce negative disparity to adapt to the common occurrence of both negative and nonnegative disparities in remote sensing stereo image pairs. For cost aggregation, we employ a 3D convolution-based encoder-decoder structure that allows the network to adaptively aggregate information. Before feature aggregation, we also introduce an attention module to retain more valuable feature information, enhance feature representation, and obtain a higher-quality disparity map. By training on the publicly available US3D dataset, we obtain the accuracy that 1.115 pixel in end-point error (EPE) and 5.32% in the error pixel ratio (D1) on the test dataset, and the inference speed is 92 ms. Comparing our model with existing state-of-the-art models, we achieve higher accuracy, and the network is beneficial for the three-dimensional reconstruction of remote sensing images.

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting healthcare quality and the nursing profession. This study employs the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in the 2018 National Sample Survey of Registered Nurses (NSSRN) dataset and predict nurse turnover using machine learning (ML) algorithms. Four ML algorithms, namely logistic regression (LR), random forests (RF), decision tree (DT), and extreme gradient boosting (XGBoost), are applied to the SMOTE-enhanced dataset. The data is randomly split into an 80% training set and a 20% validation set. Eighteen carefully selected variables from the NSSRN database serve as predictive features, and the machine learning model identifies feature importance concerning nurse turnover. The study includes a performance comparison based on metrics such as Accuracy, Precision, Recall (Sensitivity), F1-score, and AUC. In summary, the results demonstrate that SMOTE-enhanced random forests (SMOTE_RT) exhibit the most robust predictive power, both in the classical approach (with all 18 predictive variables) and an optimized approach (utilizing eight key predictive variables). XGBoost, decision tree, and logistic regression follow in performance. Notably, age emerges as the most influential factor in nurse turnover, with working hours, EHR/EMR usability, individual income, and region also playing significant roles. This research offers valuable insights for healthcare researchers and stakeholders, aiding in selecting suitable ML algorithms for nurse turnover prediction.

The sudden outbreak of the COVID-19 pandemic challenged education systems worldwide to quickly pivot their teaching-learning processes from in-person to virtual modes in order to control the spread of the virus. In a short period of time, teachers were forced to adopt new remote teaching methods to ensure the continuation of education. This paper examines how teachers in Pakistan leveraged mobile technology as an alternative teaching strategy to provide access to education during these unprecedented times. Through in-depth individual interviews with selected teachers, the study explores the potential of mobile technology to transform traditional teaching methods into interactive learning environments. The findings highlight the importance of embracing new pedagogical possibilities offered by mobile technology and the need for effective teacher professional development in the post-pandemic era. The study offers valuable insights into how mobile technology can be effectively utilized in education, even in the most challenging circumstances.

The use of Attitude and Heading Reference Systems (AHRS) for orientation estimation is now common practice in a wide range of applications, e.g., robotics and human motion tracking, aerial vehicles and aerospace, gaming and virtual reality, indoor pedestrian navigation and maritime navigation. The integration of the high-rate measurements can provide very accurate estimates, but these can suffer from errors accumulation due to the sensors drift over longer time scales. To overcome this issue, inertial sensors are typically combined with additional sensors and techniques. As an example, camera-based solutions have drawn a large attention by the community, thanks to their low-costs and easy hardware setup; moreover, impressive results have been demonstrated in the context of Deep Learning. This work presents the preliminary results obtained by DOES , a supportive Deep Learning method specifically designed for maritime navigation, which aims at improving the roll and pitch estimations obtained by common AHRS. DOES recovers these estimations through the analysis of the frames acquired by a low-cost camera pointing the horizon at sea. The training has been performed on the novel ROPIS dataset, presented in the context of this work, acquired using the FrameWO application developed for the scope. Promising results encourage to test other network backbones and to further expand the dataset, improving the accuracy of the results and the range of applications of the method.

Background: Simulation plays a crucial role in health studies, as it helps medical students apply their theoretical knowledge in real-life situations. Moulage is one of the techniques that helps in making simulation more realistic or high-fidelity. It uses special effects to emulate wounds for a better understanding of what the wound is like visually. Still, moulage is expensive, time-consuming, resource-intensive, and requires the training of staff, which is why we need to find low-cost substitutes for moulage materials. Method: When searching the database “PubMed” for the terms “Low-cost and Medical moulage”, we retrieved 222 studies, out of which when excluding results not related to low-cost, we obtained 62 studies, from which when removing studies that do not contain information regarding moulage, we found two papers, after referring to citations and cited articles of those papers, we ended up with six studies. Based on the selected articles and additional articles sourced from their reference list, a total of 11 studies were included in the review. Results: We understand that moulage is a technique that helps make simulations come alive, but the resources required to use it are at times, expensive, which is why we need to find methods to do low-cost moulage, and many studies address that it can be as simple as using homemade ingredients. Students from a previous study have talked about their opinions regarding the realistic component of moulage and whether if it is any different from other moulages. Most of the students agreed that the moulage ranked well in face and content validity. However, further innovations must be introduced in the field to be widely spread and lead to newer opportunities. Conclusion: Although the research done under moulage is limited, it is accepted that moulage is helpful for simulation-based studies and that low-cost moulage can help make medical studies a better experience for students studying it. Students have a favorable opinion on the realistic aspect of the low-cost moulage applied to them. Newer methods can be introduced to moulage, and it can be implemented in low-income countries.

One of the main challenges for autonomous learning in virtual environments is finding the right material that fits students’ needs and supports their learning process. Personalized recommender systems partially solve this problem by suggesting online educational resources to students based on their preferences. However, in educational environments (which need a proper characterization of both users and educational resources), most existing recommendation algorithms either fail to include all the available information or use hybrid processes that do not exploit possible relationships between users and item features. This article presents a personalized recommender system for educational resources aimed at combining user and item information into a single mathematical model based on matrix factorization. As a result, estimated latent factors can provide insight into possible interactions between users and item features, improving the quality of the information retrieval process. We validated the proposed model on a real dataset that contains the ratings assigned by students from Universidad Nacional de Colombia and Universidade Feevale to educational resources in the Colombian Federation of Learning Object Repositories (FROAC in Spanish). User characterization included learning style and educational level, whereas item characterization (obtained from the objects’ metadata), included interactivity level, aggregation level and type, and resource format. These results, compared to those obtained when not all the available information is included, show that our method can improve the recommendation process.

Higher education informatization (HEI) is an interdisciplinary field that examines the use and integration of information and communication technologies (ICTs) in higher education. This paper provides a bibliometric and visual analysis of the research trends, patterns, and topics in this field. Using the Web of Science database, we selected and analyzed 199 SCI and SSCI papers on HEI published from 2000 to 2023 by VOSviewer and CiteSpace software. The results indicate that the publication volume of HEI research has grown significantly in recent years, with China and the US being the most productive and influential countries. The author network shows the collaboration and contribution of different researchers and institutions, while the journal network reveals the multidisciplinary nature and scope of the field. The keyword network and the burst keyword analysis identify the main research themes and the emerging hot topics in HEI, such as online learning, big data, and artificial intelligence. The co-citation network of sources illustrates the theoretical and methodological foundations and influences of the field. The paper concludes with some implications and suggestions for future HEI research.

Synthetic Aperture Radar has been extensively used in numerous fields and can gather a wealth of information about the area of interest. This large-scene data-intensive technology puts a high value on automatic target recognition (ATR) which can free the utilizers and boost the efficiency. Recent advances in artificial intelligence have made it possible to create a deep learning-based SAR ATR that can automatically identify target features from massive input data. In the last 6 years, intensive research has been conducted in this area, however, most papers in the current SAR ATR field used recurrent neural network (RNN) and convolutional neural network (CNN)-varied models to deepen the regime’s understanding of the SAR images. To equip SAR ATR with updated deep learning technology, this paper tries to apply a lightweight vision transformer (LViT)-based model to classify SAR images. The entire structure was verified by an open- accessed SAR data set and recognition results show that the final classification outcomes are robust and more accurate in comparison with referred traditional network structures without even using any convolutional layers.

This research reviews a novel artificial intelligence (AI) based application called ‘TLDetect’, which filters and classifies anomalous glow curves (GCs) of thermoluminescent dosimeters (TLDs). Until recently, GCs review and correction in the lab were performed using an old in-house software, which uses Microsoft Access database and allows the laboratory technician to manually review and correct almost all GCs without any filtering. The newly developed application ‘TLDetect’ uses a modern SQL database and filters out only the necessary GCs for technician review. TLDetect first uses an Artificial Neural Network (ANN) model to filter out all regular GCs. Afterwards, it automatically classifies the rest of the GCs into five different anomaly classes. These five classes are defined by GCs typical patterns, i.e. high noise at either low or high temperature channels, untypical GC width (either wide or narrow), shifted GCs whether to the low or to the high temperatures, spikes, and the last class contains all other unclassified anomalies. By this automatic filtering and classification, the algorithm substantially reduces the amount of technician’s time of reviewing the GCs and makes the external dosimetry laboratory dose assessment process more repeatable, accurate and fast. Moreover, a database of GCs class anomalies distribution over time is saved along with all their relevant statistics, which can later assist with preliminary diagnosis of TLD reader hardware issues.

There is a noticeable absence of health education among college students. This study aimed to evaluate the extent of general nutrition knowledge among Chinese university students and explore its association with eating attitudes. Data were collected from a group of 273 students in Spring of 2023, using a valid and reliable research instrument consisting of three sections: demographic variables, the General Nutrition Knowledge Questionnaire (GNKQ), and the Eating Attitudes Test (EAT-26). The results were analyzed using SPSS, with correlations and t-tests to examine the relationships between nutritional knowledge and dietary attitudes. Furthermore, the present study employed the Random Forest (RF) algorithm, a machine learning technique, utilizing the Mean Decrease Impurity (MDI) method to investigate the influence of various features on participants' eating attitudes. The findings revealed that Chinese university students had an average accuracy of over 60% in their nutritional knowledge, but their understanding of the relationship between diet and disease still needs improvement. Moreover, male students had significantly lower nutritional knowledge than female students, and there was a positive correlation between nutritional knowledge and parents’ income. The study also found a significant correlation between the level of nutritional knowledge and eating attitudes. RF results indicated that family income level exhibited the most substantial impact on the eating attitudes of the participants. The study highlights the need for nutrition education curriculum developers to focus more on improving students' nutritional knowledge, with particular attention given to male students, low-income individuals, and those with an abnormal BMI.

There is no doubt that the COVID-19 pandemic has greatly affected the higher education sector in South Africa. However, academics and students’ preparedness and competencies have been considered a major conundrum concerning the integration of online learning in the classroom. The purpose of this paper is to examine the academics’ perspectives on a blend of a metaverse in the higher education sector in the post-COVID-19 era at one of the South African rural-based universities. A survey was administered in 2022 to ten (10) academics and the reports were consulted from four (4) E-learning practitioners to solicit their perceptions regarding the use of online learning and contact classes in the post-pandemic era. A qualitative research approach was employed to comprehend the challenges encountered in a historically disadvantaged rural-based university in Limpopo Province. The findings of this study show that there are major issues and challenges impeding the establishment of effective e-learning education. Consequently, technological continuity as a new normal in the post-COVID-19 era appears to be unattainable due to the challenges encountered by the students and lecturers. The use of Learning Management Systems among academics seems to have deteriorated due to the adjustments in COVID-19 rules and regulations. Furthermore, the findings revealed that most academics believed that contact learning remains irreplaceable throughout generations and ages as some are technophilic. This paper recommends that the incompetence and technological resistance and reluctance in adopting transformative pedagogies may not be used as a stumbling block to consider e-learning as a viable option to discontinue online education.

The current epoch, known as the Anthropocene, is characterized by significant human impact on the global ecological system, including altered species survival and distribution patterns due to global warming resulting from industrialization. Accurately quantifying and assessing the extent of human impact on the environment is of utmost importance. To this end, four primary methods have been developed to measure human impact: (1) ecological footprint, (2) Human appropriation of net primary production (HANPP), (3) Planetary boundary, and (4) Living Planet Index. In this paper, we aim to provide a comprehensive understanding of these methods, including their strengths and weaknesses, to evaluate their efficacy in accurately assessing the impact of human activities on the global ecosystem. Furthermore, we explore the potential of utilizing novel machine learning modelling for future predictions in this area. By analyzing and comparing these methods, we can gain insight into the ways in which human activities impact the environment and use this knowledge to inform future policies and practices to mitigate negative effects.

Face recognition is a valuable forensic tool for criminal investigators since it certainly helps in identifying individuals in scenarios of criminal activity like fugitives or child sexual abuse. It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements. Deep learning approaches for face detection have proven to be very successful but they require a large computation power and processing time. In this work, we evaluate the speed-accuracy tradeoff of three popular deep-learning-based face detectors on the WIDER Face and UFDD data sets in several CPUs and GPUs. We also develop a regression model capable to estimate the performance, both in terms of processing time and accuracy. We expect this to become a very useful tool for the end user in forensic laboratories in order to estimate the performance for different face detection options. Experimental results showed that the best speed-accuracy tradeoff is achieved with images resized to 50% of the original size in GPUs and images resized to 25% of the original size in CPUs. Moreover, performance can be estimated using multiple linear regression models with a Mean Absolute Error (MAE) of 0.113 what is very promising for the forensic field.

Longitudinal dispersion coefficient (LDC) plays an essential role in modeling the transport of pollution and sediment in the natural rivers. As a result of transportation processes, the concentration of pollution changes along the river. Different studies have been conducted to provide simple equations for estimating LDC. In this study, Support Vector Regression (SVR), Gaussian Process Regression (GPR), M5P and Random Forest (RF) examined to predict the LDC in the natural streams. The hydraulic and geometric features of different rivers gathered for developing the mentioned models for LDC estimation and various statistical criteria were utilized to scrutinize of the models. Furthermore, the Taylor chart was used to evaluate the models and achieved results showed that among machine learning models, M5P displayed the superior performance with CC of 0.823, SI of 0.812, NS of 0.577 and WI of 0.879. As well, S-D model with CC of 0.795 SI of 0.827, NS of 0.558 and WI of 0.890 had more precise results than other empirical models. The results indicates that the developed M5P model with simple formulations was superior to other machine learning models and empirical models and therefore, it can be used as a proper tool for estimating LDC in natural rivers.

In this proposed work, five systems were developed to classify four motor functions—forward hand movement (FW), grasp (GP), release (RL), and reverse hand movement (RV)—from EEG signals. The dataset used is WAY-EEG-GAL, involving participants performing a sequence of hand movements. During preprocessing, bandpass filtering was applied to remove artifacts and focus on the mu and beta frequency bands. The first system, a preliminary study model, explored the overall framework of EEG signal processing and classification. It utilized time-domain features like variance and frequency-domain features like alpha and beta power, with classification performed using a KNN model. Insights from this system informed the development of a baseline system, which uses the same dataset but different feature extraction and classification paradigms. This baseline system combined the common spatial patterns (CSP) method with continuous wavelet transform (CWT) for feature extraction and employed a GoogLeNet classifier with transfer learning. Classification was performed on six unique pairs of events derived from the four motor functions, using both intrasubject and intersubject methods. The baseline system achieved the highest accuracy of 99.73% for the GP-RV pair and the lowest accuracy of 80.87% for the FW-GP pair in intersubject classification. Building on this, three additional systems were developed to perform 4-way classification. Among these, the final model, ML-CSP-OVR, achieved the highest intersubject classification accuracy of 78.08% using all combined data and 76.39% for leave-one-out intersubject classification. This proposed model, which features a novel combination of CSP-OVR, CWT, and GoogLeNet, demonstrates strong potential as a general system for motor imagery (MI) tasks without being subject-dependent.

Machine learning methods have been a standard approach to select features that are associated with an outcome and build a prediction model when the number of candidate features is large. LASSO has been one of the most popular approaches to this end. LASSO approach selects features with large regression estimates, rather than based on statistical significance, associating the outcome, by imposing L1-norm penalty to overcome the high dimensionality of the candidate features. As a result, LASSO may select insignificant features while possibly missing significant ones. Furthermore, from our experience, LASSO has been found to select too many features. By selecting features that are not associated with the outcome, we may have to spend more cost to collect and manage them in the future use of a fitted prediction model. Using the combination of L1- and L2-norm penalties, elastic net (EN) tends to select more features than LASSO. The overly selected features that are not associated with the outcome act like white noise, so that the fitted prediction model loses the prediction accuracy. In this paper, we propose to use the standard regression methods (without any penalizing approach) with stepwise variable selection procedure to overcome these issues. Unlike LASSO and EN, this method selects features based on statistical significance. Through extensive simulations, we show that this maximum likelihood estimation based method selects very small number of features while maintaining a high prediction power, while LASSO and EN make a large number of false selections to result in loss of prediction accuracy. Contrary to LASSO and EN, the regression methods combined with a stepwise variable selection method is a standard statistical method, so that any biostatistician can use it to analyze high dimensional data even without advanced bioinformatics knowledge.

When computers start to become a dominant part of technology around the 1950s, fundamental questions about reliable designs and robustness were of great relevance. Their development gave rise to the exploration of new questions such as what made brains reliable (since neurons can die) and how computers could get inspiration from neural systems. In parallel, the first Artificial Neural Networks came to life. Since then, the comparative view between brains and computers has been developed in new, sometimes unsuspected directions. With the rise of deep learning and the development of connectomics, an evolutionary look at how both hardware and neural complexity have evolved or designed is required. In this paper, we argue that important similarities have resulted both from convergent evolution (the inevitable outcome of architectural constraints) and inspiration of hardware and software principles guided by toy pictures of neurobiology. Moreover, dissimilarities and gaps originate from the lack of major innovations that have paved the way to biological computing (including brains) that are completely absent within the artificial domain. As it occurs within synthetic biocomputation, we can also ask whether alternative minds can emerge from A.I.\ designs. Here we take an evolutionary view of the problem and discuss the remarkable convergences between living and artificial designs and what are the pre-conditions to achieve artificial intelligence.

This paper presents machine learning methods for approximate solutions of reaction-diffusion equations with multivalued interaction functions. This approach addresses the challenge of finding all possible solutions for such equations, which often lack uniqueness. The proposed method utilizes physics-informed neural networks (PINNs) to approximate generalized solutions.

In this report, we present a study demonstrating how machine learning methods can reveal the interaction of different risk factors of post-transplant leukemic relapse and obtain robust predictions even with a modest clinical dataset. Using a cohort of 63 pediatric patients with acute lymphocytic leukemia (ALL) and 46 patients with acute myeloid leukemia (AML) who underwent stem cell transplant at a single institution, we built predictive models of leukemic relapse with both pretransplant and posttransplant patient variables (specifically lineage-specific chimerism) using the random forest classifier. The random forest classifier revealed different important predictive factors between ALL and AML in our relapse models consistent with previous knowledge. Furthermore, it also distinguished donor CD34 chimerism as most impactful in relapse prediction compare to donor chimerism of other cellular lineages in our dataset for ALL but CD3 for AML. Our models greatly improved sensitivity and specificity at predicting relapses in cross validation compared to a reference model based on our own institutional incidence of relapse and inferential statistical principles. Local Interpretable Model-Agnostic Explanations, an interpretable machine learning tool, confirmed our Random Forest Classification result and provided an intuitive explanation of how our machine learning models made the relapse prediction for each individual patient.

This research aims to explore factors that influence sustainable music learning system from psychological perspective, and innovatively constructs a combination of qualitative and quantitative approaches. For first time, combines nonlinear system and identifies relevant factors affecting music learning by establishing data system for questionnaire answering and a quantitative model for actual academic performance. Existing research mainly looks at several factors that affect fragmented music learning system from perspective of teachers' teaching rules, emphasizing phased teaching state and learning goals of teachers as main body, thus ignoring music learning students, who are a large group of music learning objects. The research fills gap in this type of research object, focusing on sustainable music learning system from emotional perspective and students who occupy a dominant position in music learning, so as to more accurately explore impact of their emotional influencing factors on music learning system. The most prominent innovation of this study lies in construction of stochastic nonlinear system for psychological influencing factors of student music learning and a quantitative model for actual learning effect. Through analysis of nonlinear system, weight values of several negative emotions on music learning system are obtained. The comprehensive impact of emotional factors and practical learning on music learning system can be obtained by weighting them together.

Abstract: The Internet of Things (IoT) has witnessed rapid and widespread adoption across various domains, including transportation, healthcare, education, agriculture, urban planning, smart homes, and more. Despite its transformative potential, this pervasive deployment of IoT devices has introduced new challenges, particularly concerning security and privacy threats such as unauthorized data access and device breaches. The excessive usage of these technological devices, coupled with the absence of robust security and privacy systems for user data, calls for a comprehensive approach to address these issues. In this study, we propose a novel framework designed to analyze, audit, test, and detect potential vulnerabilities within IoT environments and applications. The central components of the proposed framework include a machine learning algorithm for data classification and attack detection, along with the integration of Blockchain technology to enhance security measures. Specifically, the framework performs an in-depth analysis of user data to identify potential security or privacy vulnerabilities. Additionally, it conducts rigorous testing of smart services and automated data-collecting devices. To evaluate the effectiveness of our classification algorithm, we conducted a comprehensive implementation on a real-world IoT dataset. The results showcased the efficiency and accuracy of our approach in detecting and mitigating potential threats. Furthermore, based on our research findings, we provide valuable recommendations for enhancing security and privacy in IoT ecosystems. We also highlight emerging trends in the security and privacy domains, which can serve as valuable insights for researchers and practitioners. In conclusion, our proposed framework offers a robust and proactive approach to address the security and privacy challenges, such as unauthorized data access and device breaches posed by the widespread adoption of IoT devices. By combining machine learning algorithms and Blockchain technology, we contribute to safeguarding user data and fostering a secure environment for IoT applications. This study lays the groundwork for further advancements in the realm of IoT security and privacy, ensuring a safer and more resilient IoT landscape for the future.

Mobility is a vital welfare indicator which may influence broilers’ daily activities. Classical broiler mobility assessment methods are laborious and cannot provide timely insights into their conditions. Here, we proposed a semi-supervised Deep Learning (DL) model, YOLOv5, combined with Deep Sort algorithm conjoined with our newly proposed algorithm, Neo-Deep Sort, for individual broiler mobility tracking. Initially, 1,650 labeled images from five days were employed to train the YOLOv5 model. Through semi-supervised learning (SSL), this narrowly trained model was then used for pseudo-labeling 2,160 images, of which 2,153 were successfully labeled. Thereafter, the YOLOv5 model was fine-tuned on the newly labeled images. Lastly, the trained YOLOv5 and the Neo-Deep Sort algorithm were applied to detect and track 28 broilers in two pens and categorized them in terms of hourly and daily traveled distances and speeds. SSL helped in increasing the YOLOv5 model’s mean Average Precision (mAP), in detecting birds, from 81% to 98%. As compared with the manually measured covered distances of broilers, the combined model provided individual broiler's hourly moved distances with a validation accuracy of about 80%. Eventually, individual and flock level mobilities were quantified while overcoming the occlusion, false and miss detection issues.

The robust control of high precision electromechanical systems, such as micropositioners, is challenging in terms of the inherent high nonlinearity, the sensitivity to external interference, and the complexity of accurate identification of the model parameters. To cope with these problems, this work investigates a disturbance observer-based deep reinforcement learning control strategy to realize high robustness and precise tracking performance. Reinforcement learning has shown great potential as optimal control scheme, however, its application in micropositioning systems is still rare. Therefore, embedded with the integral differential compensator (ID), deep deterministic policy gradient (DDPG) is utilized in this work with the ability to not only decrease the state error but also improves the transient response speed. In addition, an adaptive sliding mode disturbance observer (ASMDO) is proposed to further eliminate the collective effect caused by the lumped disturbances. The sterling performance is revealed with intensive tracking simulation experiments and demonstrates the improvement in the accuracy and response time of the controller.

The present work proposed a low-cost portable device as an enabling technology for Smart Farms using multispectral imaging and Machine Learning in soil texture. Clay is an important factor for the verification and monitoring of soil use due to its fast reaction to chemical and surface changes. The system developed uses the analysis of reflectance in wavebands for clay prediction. The selection of each wavelength is performed through an LED lamp panel. A NoIR microcamera controlled by a Raspberry Pi device is employed to acquire the image and unfold it in RGB histograms. Results showed an good prediction performance with R2 of 0.96, RMSEC of 3.66% and RMSECV of 16.87%. The high portability allows the equipment to be used in a field providing strategic information related to soil sciences.