This study employs a multilayer network approach to analyze the spatial and temporal patterns of suicide and depression across Mexican municipalities from 2015 to 2020. Using a panel dataset of mental health cases, substance use, and healthcare infrastructure, we constructed a multilayer graph based on cosine similarity. The Infomap clustering algorithm was then applied to identify communities of municipalities with similar mental health profiles. Our results reveal five distinct clusters with significant variations in the levels and temporal dynamics of the analyzed indicators. Notably, two clusters consistently exhibited higher rates of substance use and adverse mental health outcomes. These findings demonstrate the efficacy of network-based methods for identifying at-riskmunicipal groupings, thereby informing targeted public health interventions.
Plant diseases are the main factor in plant mortality and destruction, especially in trees. Early discovery, however, can assist to manage and treat this issue efficiently. To increase output, crop and plant lesions are detected and stopped as soon as feasible. Because it relies solely on visual observation, manual inspection of plant leaf diseases is time-consuming and expensive. The authors offer methods for identifying and categorizing plant leaf diseases using computer vision. Pre-processing original images to visualize contaminated areas, feature extraction from unprocessed or segmented images, feature fusion, feature selection, and classification are a few examples of computer vision approaches. The fusion technique is used to combine the target's numerical data features, which go beyond the picture, with the extracted image features to increase the target's feature representation. The following are the principal issues that researchers found in the literature: Low-contrast infected regions. Extract redundant and irrelevant information, which degrades classification accuracy; Redundant and irrelevant information may lengthen computation times and the targeted models performance will suffer as a result. This study proposed a framework for classifying plant leaf diseases based on the best feature selection and a deep learning fusion model. In the suggested approach, contrast is first enhanced using a pre-processing model, and then the issue of an unbalanced dataset is resolved via data augmentation. The proposed Deep Fusion Learning Model (DFLM) shows an accuracy of 98.8% in comparison with other models.
Anxiety during pregnancy constitutes a relevant factor that can significantly influence labor development. This study presents a novel approach based on explainable artificial intelligence to predict both the type and duration of labor using psychological indicators of anxiety prior to delivery. Employing data from 235 full-term pregnant women from two Spanish hospitals, we developed a multilayer perceptron model to classify eutocic and dystocic deliveries, achieving a capacity to identify 88\% of dystocic deliveries. Additionally, we implemented a regression model that predicts labor time with a mean error of 2 hours, correctly predicting 86% of cases with an error margin of less than 3 hours. The application of explainability techniques to the developed models allows for understanding the specific influence of each anxiety factor on labor development. These results demonstrate the potential of AI models to improve obstetric care and optimize healthcare resource allocation.
Aspect-based sentiment analysis is a process aimed to understanding the sentiment expressed in opinions or reviews about specific features of an entity. The automatic extraction of aspects is the most challenging task, as it requires the ability to understand the context and to recognize the relevant and characteristic elements of an entity about which you have an opinion. To increase the quality results in the solution to this problem is still a challenge in Spanish reviews, because very few papers have been reported and the reported efficacy rates need to be improved. The use of deep learning models has proven an advantage for aspect extraction task, but the combination of several models for obtaining a final prediction has not yet been exploited. In this work, an aspect extraction method in which several Transformer models are combined through an ensemble learning approach using the Average Voting technique is presented. The proposed solution was evaluated using the SemEval2016 dataset and the results obtained were compared to those reported by other state-of-the-art solutions. The evaluation process not only provides a starting point to have a broader perception of the performance of the Transformers in this context, but also highlights the improvement of the quality results of the aspect extraction with the Transformers-Based Ensemble
In the field of AI, word embedding models have proven to be one of the most effective methods for capturing semantic and syntactic relationships between words, enabling significant advancements in natural language processing. However, producing word embeddings for low-resource indigenous languages-such as Yucatec Maya-often suffers from poor reliability due to limited data availability and unsuitable evaluation benchmarks. In this work, we propose a novel methodology for constructing reliable word embeddings by adapting the Swadesh List for semantic similarity evaluation. Our approach involves translating the Swadesh List from a high-resource pivot language into the target language, applying linguistic and cultural filtering, and correlating similarity scores between pivot-language embeddings from large language models and target-language embeddings. Our results demonstrate that this method produces reliable and interpretable embeddings for Yucatec Maya. Furthermore, our analysis provides compelling evidence that the choice of evaluation benchmark has a far greater impact on reported performance than hyperparameter optimization. This approach establishes a robust new framework with the potential to be adapted for improving word embedding generation in other low-resource languages.
In recent years, the rise in diabetic retinopathy cases has posed significant challenges to existing computer-aided diagnosis (CAD) solutions. These systems often focus on detecting specific abnormalities, such as microaneurysms, exudates, or hemorrhages, rather than providing a comprehensive diagnostic approach. Moreover, state-of-the-art deep learning-based methods face critical limitations, including a lack of contextual understanding, gradient vanishing/explosion issues, and failure to address class imbalance at the instance level, which impacts multi-class classification accuracy. To overcome these challenges, a novel diabetic retinopathy prediction model is proposed, leveraging firefly heuristic segmentation and residual deep spatio-textural feature learning. Instead of processing entire fundus images, the model applies Firefly heuristic-driven Fuzzy C-Means (FFCM) clustering to segment regions of interest (ROIs) corresponding to microaneurysms, exudates, and hemorrhages. Residual deepspatio-textural features are then extracted using Gray-Level Co-occurrence Matrix (GLCM), ResNet50, and AlexNet. These complementary features enhance diversity and heterogeneity, which are further processed using random forest learning. The proposed model achieves outstanding performance, with an average accuracy of 99.77%, precision of 99.88%, recall of 99.64%, F-measure of 99.75%, sensitivity of 99.64%, and specificity of 99.86%, surpassing existing approaches. FFCM mitigates the class imbalance problem, ResNet50 addresses gradient challenges, and AlexNet contributes high-dimensional features, ensuring robust and scalable diagnostics. This innovative solution demonstrates exceptional generalizability and runtime efficiency, offering a cost-effective, comprehensive CAD tool for diabetic retinopathy detection.
Internet of Things (IoT) has brought unprecedented opportunities across various sectors, including healthcare, transportation, industrial automation, and smart cities. However, this expansion has also introduced significant security vulnerabilities due to the heterogeneous nature, limited computational capabilities, and large-scale deployment of IoT devices. Detecting anomalies, which often signify security breaches or system malfunctions, is crucial to maintaining the integrity and reliability of IoT systems. Traditional anomaly detection methods, typically rule based or signature driven, struggle to adapt to evolving threats and diverse data patterns in IoT networks. This paper proposes a novel architecture named NAIIDS4IoT (Novel Artificial Intelligence-based Intrusion Detection System architecture for IoT), designed to provide efficient, accurate, and scalable anomaly detection using Artificial Intelligence. The core of NAIIDS4IoT lies in the integration of federated learning with deep autoencoders, enabling decentralized model training across edge devices without sharing raw data, thereby preserving user privacy and reducing communication overhead. Each edge node independently learns patterns of normal behavior and identifies anomalies based on reconstruction errors. A global model is continuously refined through collaborative learning across nodes. Furthermore, NAIIDS4IoT incorporates lightweight encryption and blockchain based model integrity verification to enhance security and trust in the detection process. Experimental validation using real-world IoT datasets demonstrates that NAIIDS4IoT achieves high detection accuracy, low false positive rates, and strong adaptability to dynamic environments, significantly outperforming conventional centralized and shallow learning based solutions. This architecture represents a significant step toward intelligent, autonomous, and privacy-preserving anomaly detection in next generation IoT ecosystems.
The global coffee industry faces significant challenges from crop diseases, of which coffee leaf rust (CLR) caused by the fungus Hemileia vastatrix, stands out as one of the most damaging. Accurate assessment of disease severity is essential for applying effective control strategies. In response to this need, this study introduces a modern approach using deep learning and image processing techniques to identify and quantify CLR injury automatically. We developed thirteen models using convolutional neural networks, to classify lesions into different degrees of severity. It offers a promising alternative to conventional methods, especially under data-limited conditions, although some limitations remain in robustness across datasets. Manual rust detection requires close visual inspection of leaves, a laborious and error-prone process, especially in large cultivation areas. This challenge makes it harder to apply timely and effective disease management strategies.
Alzheimer’s disease (AD) is a neurological disorder that causes memory decline and loss of cognitiveabilities. AD directly impacts the brain activity of affected individuals, which can be reflected inelectroencephalogram (EEG) signals. Previous studies have typically relied on statistical, spectral, and waveletfeatures in order detect AD using EEG signals. Recurrence Quantification Analysis (RQA) is a non-lineartechnique that has been successfully used to analyze EEG signals in several other domains including emotionrecognition and autism detection. However, RQA features have not yet been fully investigated for AD diagnosis.The aim of this work is to thoroughly investigate the usefulness of RQA features for AD diagnosis. Fifteen RQAfeatures were computed along with statistical measures, Hjorth parameters, and relative power in order to comparethe performance of the RQA features to other commonly utilized EEG features. All features were computed fromthe different brain regions. Experimental results indicated that RQA features outperformed all other feature groupsregardless of the considered brain region. RQA features achieved accuracies ranging from 89.6% to 98.2% using asupport machine vector (SVM) classifier with leave-one-subject-out (LOSO) cross-validation. These results arebetween 25% to 40% higher than the three other considered feature groups. Feature ranking was performed to findthe most relevant RQA features, identifying seven of the fifteen computed RQA features. This work sheds light onthe potential of RQA features for reliable AD diagnosis and paves the way for their integration in computer-aidedAD diagnostic tools using EEG signals.
The widespread use of unmanned aerial vehicles in a variety of sectors poses major challenges to these issues of cyber security and data protection. In this paper, a detailed study of the security vulnerabilities in UAV-based systems was conducted and analytically categorized into three types: Software, hardware and communication links. These vulnerabilities include access rights without authentication, control channel tampering, data breaches and spoofing of the global positioning system. These vulnerabilities jeopardize the security, integrity of the data and privacy of not only the drone but also the users. The study analyzes some of the security protocols that aim to mitigate these risks. They range from advanced encryption techniques to authentication mechanisms and intrusion detection systems that can use classification models based on machine learning. The study also provides a context in which emerging technologies such as blockchain, machine learning and deep learning can make a greater contribution to securing drones. The detailed and in-depth discussion on the development of the security solution that the work provides emphasizes the importance of securing UAV operations and their data integrity aspects alongside securing public trust for autonomous systems.
In particular, Rumex weed detection is regarded as a crucial step in real-world data under many circumstances. The detection task suffers from several issues, such as overlapping weeds, occlusion, varying leaf colour distributions, leaf size and shape, and growth stage. Many machine learning techniques have been proposed to detect weeds in plants. These techniques suffer from locating weed with precise bounding boxes because they may contain multiple bounding boxes in a certain region. Researchers have used the R-CNN based weed identification system, but it continues to have a low detection rate because of the issues mentioned above. In order to detect Rumex weeds under various conditions, particularly overlapping, occlusion, and size, as well as containing multiple bounding boxes, this paper is developed the R-CNN model by using UNet instead of the CNN model to become R-UNet. The proposed model is used due to its novelty of using a UNet classifier with selective regions which boosts the detection capabilities by extracting the most helpful features more effectively than the CNN network. The proposed method uses Intersection over Union (IoU) to assess the detection rate using real-world data. We compare and benchmark the evaluation of the detection performance of this work with different models, including Single-Shot Detector (SSD), hybrid CNNs, AlexNet, and adapted NMS methods. The proposed model yields the highest IoU values compared with other methods.
Optimization problems are complex problems that are very difficult to solve. Although these types of problems are solved in the real world using exact methods, these methods are very time-consuming and costly. By using soft computing methods, the time and cost of problem-solving can be reduced to some extent. Engineering problems are among the complex real-world problems that can be solved through soft computing methods. One of these methods is the use of metaheuristic algorithms to optimize the solution of these types of problems. The Particle Swarm Optimization (PSO) algorithm is a common and state-of-the-art metaheuristic algorithm used to solve engineering optimization problems. This algorithm is known as swarm-based optimization techniques and has a very powerful mathematical basis. Another recently published algorithm is the Giza Pyramids Construction (GPC) algorithm. The GPC algorithm models the technological advancements of construction in ancient times. Both algorithms have many advantages through which optimization problems can be solved effectively. To increase the power of metaheuristic algorithms and solve optimization problems more effectively through them, the idea of competitive hybridization algorithms has been proposed. In this paper, two competitive hybrid approaches of combining PSO and GPC algorithms are presented. These two competitive hybridization approaches have been first applied to 45 benchmark functions and have been evaluated and analyzed statistically. Then they have been applied to six classic engineering problems. Algorithms presented in each step have been compared with Genetic Algorithm (GA) and PSO algorithms and their combined approaches. The results of experiments and statistical analysis show that the solution to engineering problems has been done more effectively by using the two proposed combinations.
Dental age estimation (DAE) is important in age-related studies ranging from forensics, clinical dentistry and bioanthropology. DAE heavily relies on image analysis and morphometrics and has underwent academic scrutiny to improve its level of reliability and accuracy. The recent rise of artificial intelligence (AI) in data analysis allows accurate analysis without the influence of human error. As AI has penetrated DAE research, there is a lack of scientometric analysis regarding AI-driven DAE studies. This scientometric study presents an analysis of AI-driven DAE research based on data from the Scopus and Web of Science literature databases. This study examines various parameters, such as publication trends, prolific countries and research institutions, active journals and highly cited publications as well as highly used keywords pertaining to AI-driven DAE studies. Notably, though the niche area is fairly recent, there has been a substantial increase in the number of publications in AI-driven DAE research in the past few years. Countries such as China, Malaysia and South Korea are currently at the forefront of publications on the application of AI in DAE studies. This study also finds that a variety of journals ranging from dentistry, law, forensics and computer science are publishing studies on AI-driven DAE. Prominent keywords such as “age estimation”, “artificial intelligence” and age-group related keywords were amongst the dominant keywords used. This scientometric analysis provides an overview of studies pertaining to AI-driven DAE, which serves to help researchers stay informed regarding the latest research trend and may help identify possible research gaps.
This research proposes an effective and reliable deep learning method for detecting brain abnormalities via magnetic resonance imaging (MRI). The technique consists of two primary stages: first, a binary classifier that divides pictures into "Brain" and "Non-Brain" categories; second, multi-class classifiers that explicitly recognise categories such pituitary adenomas, gliomas, and meningiomas. The labelled and preprocessed data were taken from a collection of 7,753 pictures provided by Qhills Technologies Pvt. Ltd. Additional data from the Brain Tumour MRI collection was also incorporated to improve the model's generalisation skills. VGG-16 outperforms the other machine learning models, with an accuracy rate of 96.4%, when compared to ANN, CNN, VGG-16, and AlexNet. A thorough model evaluation and hyperparameter tweaking process was conducted using the accuracy, precision, recall F1-score. The findings of this study point to the potential of deep learning techniques in identifying brain disorders fast and precisely, opening the door to more precise diagnosis in clinical settings.
In this work, we present a disciplinary e-tutoring system that integrates ONTO-TDM, an ontology designed for teaching domain modeling, with advanced transformer technology. Our primary objective is to enhance semantic similarity tasks within the system by fine-tuning a Sentence Transformer model. By carefully adjusting training parameters with a curated dataset of question-answer pairs focused on algorithms and data structures, we achieved a notable improvement in system performance. The Sentence Transformer model, combined with domain ontology, achieved an accuracy of 91%, a precision of 93%, a recall of 89%, and an F1-score of 90%, significantly surpassing the results of existing works. This methodology highlights the potential to deliver personalized support and guidance in tutoring scenarios. It effectively addresses the evolving needs of modern education by offering tailored answers and reducing the necessity for constant learner-tutor interaction, thereby improving the efficiency of educational support systems.
Researchers are concentrating on developing technologies to identify and caution drivers against driving while distracted because it is a major cause of traffic accidents. According to the National Highway Traffic Safety Administrator's report, distracted driving is to blame for roughly one in every five car accidents.Our goal is to create an accurate and dependable method for identifying distracted drivers and alerting them to their lack of focus. We take inspiration from the success of convolutional neural networks in computer vision to do this. Our strategy entails putting in place a CNN-based system that can recognize when a driver is distracted as well as pinpoint the precise cause of their preoccupation. Real-time detection, however, necessitates three apparently mutually exclusive requirements for an optimal network: a small number of parameters, high accuracy, and fast speed.
The integration of technology in elementary education offers innovative ways to enhance learning. One such advancement is the use of three-dimensional holograms (3DH), which provide immersive displays that merge seamlessly with the learner’s environment, creating a dynamic and engaging atmosphere. Educators have found that 3D visual tools significantly improve student comprehension, with 94.4% agreeing in a preliminary study. However, using interactive 3D holography alone has limitations, such as the inability for students to physically touch or manipulate holographic objects. To address this, Active Learning with Holo-Kid (ALHK) is introduced as a desktop application for elementary school students (grades 1 to 6). ALHK combines Leap Motion technology’s precision with interactive 3D holography to overcome these limitations. The combination allows students to interact with virtual objects in a more immersive and realistic manner. Holograms provide visual representation, while Leap Motion enables precise gesture recognition and hand tracking, resulting in a seamless and intuitive user experience. Initial evaluations demonstrate improved student engagement and comprehension. Future iterations aim to enhance scalability by incorporating features like custom object upload, multi-user interaction, and broader age applicability. ALHK shows promise as a tool for creating an immersive and intuitive learning environment using 3D holograms and interactive technology in elementary education.
In this work, we propose an approach to determine terrain traversability for a car-like robot. Our approach has two main modules: a neural network classifier that makes use of sensors' readings to assign traversability levels to control inputs of the robot, and a second neural network that, based on the outputs of the first network, mimics the control selection performed by a human driver. The approach incorporates sensor fusion from a variety of sources to enhance the traversability estimation, and it is trained employing a semi-supervised learning scheme with examples resulting from the interaction of the car with the environment. This semi-supervised scheme avoids exhausting manual labeling and is built on the premise that there is a correlation between the terrain traversability and the required and observed behaviors of the vehicle. The method is validated with data obtained from a physical electric car.
Deep learning methods have recently emerged as a mechanism for generating embeddings of planning states without the need to predefine feature spaces. In this work, we advocate for an automated, cost-effective and interpretable approach to extract representative features of planning states from high-level language. We present a technique that builds up on the objects type and yields a generalization over an entire planning domain, enabling to encode numerical state and goal information of individual planning tasks. The proposed representation is then evaluated in a task for learning heuristic functions for particular domains. A comparative analysis with one of the best current sequential planner and a recent ML-based approach demonstrate the efficacy of our method in improving planner performance.
Speech signals often contain different forms of background and environmental noise. For the development of an efficient speech recognition system, it is essential to preprocess noisy speech signals to reduce the impact of these disturbances. Notably, prior research has paid limited attention to pink and babble noises. This gap in knowledge inspired us to develop and implement hybrid algorithms tailored to handle these specific noise types. We introduce a hybrid method that combines the Bionic Wavelet transform with Adaptive Filtering to enhance signal strength. The performance of this method is assessed using various metrics, including Mean Squared Error, Signal-to-Noise Ratio, and Peak Signal-to-Noise Ratio. Notably, our findings indicate that SNR and PSNR metrics are especially effective in enhancing the handling of pink and babble noises.
