Search

Pharmacogenetics is a branch of genomic medicine aiming to personalize drug prescription guidelines based on individual genetic information. This concept might lead to a reduction in adverse drug reactions, which place a heavy burden on individual patients' health and the economy of the healthcare system. The aim of this study was to present insights gained from the pharmacogenetics-based clustering of over 500 patients from the Croatian population. The data used in this article were obtained by the pharmacogenetic testing of 522 patients from the Croatian population. The patients were clustered based on the genotypes of 28 pharmacologically relevant genes. Dimensionality reduction was employed using the UMAP algorithm, after which clusters were defined using HDBSCAN. Validation of clustering was performed by decision tree analysis and predictive modeling using the RandomForest, XGBoost, and ExtraTrees classification algorithms. The clustering algorithm defined six clusters of patients based on two UMAP components (silhouette score = 0.782). Decision tree analysis demonstrated CYP2D6 and SLCO1B1 genotypes as the main points of cluster determination. Predictive modeling demonstrated an excellent ability to discern the cluster of each patient based on all genes (avg. ROC-AUC = 0.998), CYP2D6 and SLCO1B1 (avg. ROC-AUC = 1.000), and CYP2D6 alone (avg. ROC-AUC = 0.910). Membership in each cluster provided clinically relevant information, in the context of ruling out certain favorable or unfavorable phenotypes. However, this study's main limitation is its cohort size. Through further research and investigation of a larger number of patients, more accurate and clinically applicable associations between pharmacogenetic genotypes and phenotypes might be discovered. [ABSTRACT FROM AUTHOR]

Studying sleep stages is crucial for understanding sleep architecture, which can help identify various health conditions, including insomnia, sleep apnea, and neurodegenerative diseases, allowing for better diagnosis and treatment interventions. In this paper, we explore the effectiveness of generalized weighted permutation entropy (GWPE) in distinguishing between different sleep stages from EEG signals. Using classification algorithms, we evaluate feature sets derived from both standard permutation entropy (PE) and GWPE to determine which set performs better in classifying sleep stages, demonstrating that GWPE significantly enhances sleep stage differentiation, particularly in identifying the transition between N1 and REM sleep. The results highlight the potential of GWPE as a valuable tool for understanding sleep neurophysiology and improving the diagnosis of sleep disorders. [ABSTRACT FROM AUTHOR]

Tornadoes are severe convective weather exhibiting localized and sudden occurrences. Weather radar is widely regarded as the most effective tool for monitoring tornadoes and issuing early warnings. Dual-polarization updating has significantly improved tornado prediction and forecasting abilities. This article proposes an innovative tornado detection algorithm based on XGBoost which is suitable for dual-polarization radar data, was upgraded and has been used in China since 2019, and has been applied in the Tornado Key Open Laboratory of the China Meteorological Administration. The characteristics associated with the velocity attributes, reflectivity, velocity spectrum width, differential reflectivity, and correlation coefficient are used in the algorithm to achieve real-time tornado detection. Experimental evaluations have demonstrated that the proposed algorithm significantly improves tornado detection rates and leading times. Compared with the traditional TDA-RF algorithm based on Doppler weather radar data, the TDA-XGB algorithm introduces dual polarization parameters (such as differential reflectivity and the correlation coefficient), which effectively improves tornado identification performance. In addition, the TDA-XGB algorithm combines artificial intelligence-assisted learning to optimize the traditional algorithm based on the tornado vortex signature (TVS) and tornado debris signature (TDS), further improving the detection effect. Furthermore, the algorithm provides classification probabilities in the genesis and evolution of tornadoes, thereby supporting forecasters in their efforts to anticipate and issue timely tornado warnings. [ABSTRACT FROM AUTHOR]

People tend to share their opinions on social media daily. This text needs to be accurately mined for different purposes like enhancements in services and/or products. Mining and analyzing Arabic text have been a big challenge due to many complications inherited in Arabic language. Although, many research studies have already investigated the Arabic text sentiment analysis problem, this paper investigates the specific research topic that addresses Arabic comparative opinion mining. This research topic is not widely investigated in many research studies. This paper proposes a lexicon-based framework which includes a set of proposed algorithms for the mining and analysis of Arabic comparative sentences. The proposed framework comprises a set of contributions including an Arabic comparative sentence keywords lexicon and a proposed algorithm for the identification of Arabic comparative sentences, followed by a second proposed algorithm for the classification of identified comparative sentences into different types. The framework also comprises a third proposed algorithm that was developed to extract relations between entities in each of the identified comparative sentence types. Finally, two proposed algorithms were developed for the extraction of the preferred entity in each sentence type. The framework was evaluated using three different Arabic language datasets. The evaluation metrics used to obtain the evaluation results include precision, recall, F-score, and accuracy. The average values of the evaluation metrics for the proposed sentences identification algorithm reached 97%. The average evaluation values of the evaluation metrics for the proposed sentence type identification algorithm reached 96%. Finally, the average results showed 97% relation word extraction precision for the proposed relation extraction algorithm. [ABSTRACT FROM AUTHOR]

Accurate indoor positioning is essential for many applications. However, current methods often fall short in complex environments due to signal fluctuations. We propose a new indoor positioning approach, that is, improved sequential deep learning (ISDL), to address this issue. First, we apply sequential classification algorithms to progressively narrow the search space, reducing potential location regions into smaller neighborhoods. Next, we combine a deep neural network (DNN) with Weighted K-Nearest Neighbors (WKNN) to refine the final location prediction. Then, we validate our method using the publicly available U J I n d o o r L o c dataset, demonstrating superior accuracy compared to existing methods. Specifically, we achieved 95% floor prediction accuracy and reduced the average positioning error to just 7.82 m. By combining sequential classification and the DNN-WKNN hybrid model, we achieve better localization in complex indoor environments. This system offers practical improvements for real-time location-based services and other applications requiring precise indoor positioning. [ABSTRACT FROM AUTHOR]

The increasing demand for hazelnut kernels is favoring an upsurge in hazelnut cultivation worldwide, but ongoing climate change threatens this crop, affecting yield decreases and subject to uncontrolled pathogen and parasite attacks. Technical advances in precision agriculture are expected to support farmers to more efficiently control the physio-pathological status of crops. Here, we report a straightforward approach to monitoring hazelnut trees in an open field, using aerial multispectral pictures taken by drones. A dataset of 4112 images, each having 2Mpixel resolution per tree and covering RGB, Red Edge, and near-infrared frequencies, was obtained from 185 hazelnut trees located in two different orchards of the Piedmont region (northern Italy). To increase accuracy, and especially to reduce false negatives, the image of each tree was divided into nine quadrants. For each quadrant, nine different vegetation indices (VIs) were computed, and in parallel, each tree quadrant was tagged as "healthy/unhealthy" by visual inspection. Three supervised binary classification algorithms were used to build models capable of predicting the status of the tree quadrant, using the VIs as predictors. Out of the nine VIs considered, only five (GNDVI, GCI, NDREI, NRI, and GI) were good predictors, while NDVI SAVI, RECI, and TCARI were not. Using them, a model accuracy of about 65%, with 13% false negatives was reached in a way that was rather independent of the algorithms, demonstrating that some VIs allow inferring the physio-pathological condition of these trees. These achievements support the use of drone-captured images for performing a rapid, non-destructive physiological characterization of hazelnut trees. This approach offers a sustainable strategy for supporting farmers in their decision-making process during agricultural practices. [ABSTRACT FROM AUTHOR]

Curcumae Longae Rhizoma (CLRh), Curcumae Radix (CRa), and Curcumae Rhizoma (CRh), derived from the different medicinal parts of the Curcuma species, are blood-activating analgesics commonly used for promoting blood circulation and relieving pain. Due to their certain similarities in chemical composition and pharmacological effects, these three herbs exhibit a high risk associated with mixing and indiscriminate use. The diverse methods used for distinguishing the medicinal origins are complex, time-consuming, and limited to intraspecific differentiation, which are not suitable for rapid and systematic identification. We developed a rapid analysis method for identification of affinis and different medicinal materials using attenuated total reflection-Fourier-transform infrared spectroscopy (ATR-FTIR) combined with machine learning algorithms. The original spectroscopic data were pretreated using derivatives, standard normal variate (SNV), multiplicative scatter correction (MSC), and smoothing (S) methods. Among them, 1D + MSC + 13S emerged as the best pretreatment method. Then, t-distributed stochastic neighbor embedding (t-SNE) was applied to visualize the results, and seven kinds of classification models were constructed. The results showed that support vector machine (SVM) modeling was superior to other models and the accuracy of validation and prediction was preferable, with a modeling time of 127.76 s. The established method could be employed to rapidly and effectively distinguish the different origins and parts of Curcuma species and thus provides a technique for rapid quality evaluation of affinis species. [ABSTRACT FROM AUTHOR]

In contemporary computer vision, deep learning-based real-time single image super-resolution approaches have gained significant attention for their ability to enhance the resolution of images in real time. These approaches are interconnected with various other computer vision domains, including image segmentation and object detection. Numerous surveys have summarized the state of the image SR domain. However, there is no survey that specifically addresses real-time single image SR on IoT devices. Therefore, in this study, we aim to explore strategies, identify the technical challenges, and outline the future directions of SR research, with a special emphasis on real-time super-resolution techniques. We begin with an overview of the core concepts related to real-time SR, recent challenges, and algorithm classification and delve into potential application scenarios that merit attention. Additionally, we explore the challenges and identify promising research areas related to real-time SR specifically related to IoT devices, highlighting potential advancements, limitations, and opportunities for future innovation in this rapidly evolving field. [ABSTRACT FROM AUTHOR]

This study investigates the impact of patient stress on COVID-19 screening. An attempt was made to measure the level of anxiety of individuals undertaking rapid tests for SARS-CoV-2. To this end, a galvanic skin response (GSR) sensor that was connected to a microcontroller was used to record the individual stress levels. GSR data were collected from 51 individuals at SARS-CoV-2 testing sites. The recorded data were then compared with theoretical estimates to draw insights into stress patterns. Machine learning analysis was applied for the optimization of the sensor results. Classification algorithms allowed the automatic reading of the sensor results and individual identification as "stressed" or "not stressed". The findings confirmed the initial hypothesis that there was a significant increase in stress levels during the rapid test. This observation is critical, as heightened anxiety may influence a patient's willingness to participate in screening procedures, potentially reducing the effectiveness of public health screening strategies. [ABSTRACT FROM AUTHOR]

With the integration of power converters into the power grid, it becomes crucial for the Transmission System Operator (TSO) to ascertain whether they are operating in Grid Forming or Grid Following modes. Due to intellectual properties, classification can only be performed based on non-intrusive measurements and models, such as admittance at the PCC. This classification poses a challenge as the TSO lacks precise knowledge of the actual control structures and algorithms. This paper introduces a novel classification algorithm based on Convolutional Neural Networks (CNN), capable of detecting patterns in sequential data. The proposed CNN utilizes a new architecture to separate admittances along the d and q axes, and a decision layer allows to determine the correct converter mode. The performance of the proposed CNN model was assessed through two tests and compared to the traditional feedforward model. The proposed CNN architecture demonstrates significant classification capabilities, as it is able to identify the control mode of the converter even when its control structure is not part of the training dataset. [ABSTRACT FROM AUTHOR]

Substations are an important part of the power system, and the classification of abnormal substation scenes needs to be comprehensive and reliable. The abnormal scenes include multiple workpieces such as the main transformer body, insulators, dials, box doors, etc. In this research field, the scarcity of abnormal scene data in substations poses a significant challenge. To address this, we propose a few-show learning algorithm based on two-stage contrastive learning. In the first stage of model training, global and local contrastive learning losses are introduced, and images are transformed through extensive data augmentation to build a pre-trained model. On the basis of the built pre-trained model, the model is fine-tuned based on the contrast and classification losses of image pairs to identify the abnormal scene of the substation. By collecting abnormal substation images in real scenes, we create a few-shot learning dataset for abnormal substation scenes. Experimental results on the dataset demonstrate that our proposed method outperforms State-of-the-Art few-shot learning algorithms in classification accuracy. [ABSTRACT FROM AUTHOR]

The log files of Massive Open Online Courses (MOOCs) reveal useful information that can help interpret student behavior. In this study, we focus on student performance based on their access to course resources and the grades they achieve. We define states as the Moodle resources and quiz grades for each student ID, considering participation in resources such as wikis and forums. We use efficient Hidden Markov Models to interpret the abundance of information provided in the Moodle log files. The transitions among certain resources for each student or groups of students are determined as behaviors. Other studies employ Machine Learning and Pattern Classification algorithms to recognize these behaviors. As an example, we visualize these transitions for individual learners. Additionally, we have created row and column charts to present our findings in a comprehensible manner. For implementing the proposed methodology, we use the R programming language. The dataset that we use was obtained from Kaggle and pertains to a MOOC of 4037 students. [ABSTRACT FROM AUTHOR]

As an effective computer-aided diagnostic tool, deep learning has been successfully applied to the classification of breast histopathological images. However, the performance of the deep model is data-driven, and it is difficult to obtain satisfied results when the number of histopathological images is small and labelling histopathological images is difficult. Moreover, in traditional deep learning methods, the representation of features is monotonous, which leads to the limitation of the classification performance of the model. This study proposes an auto-encoder reconstructed semi-supervised domain adaptation for a breast histopathological image classification algorithm. First, the model was pre-trained and transferred to extract high-level features of the sample images. Then, the encoding and decoding parts of the auto-encoder were used to reconstruct the feature representation learning and the sample feature reconstruction learning, respectively. This ensured that the useful information for the classification was purified and retained. At the same time, the domain discriminator was used to confuse the source and target domain features to enhance the learning ability of the model. Finally, the distribution difference of features at different depths of the auto-encoder was measured to minimize the discrepancy of feature distribution between domains, so as to complete the classification of histopathological images. Compared to the results of the comparative and ablation algorithms from the BreakHis to SNL datasets, the proposed method achieved the best results in terms of F1 score (93.40%), accuracy (95.24%), sensitivity (94.66%), and specificity (95.56%). The experimental results demonstrate that the proposed method achieves a remarkable classification performance. [ABSTRACT FROM AUTHOR]

With the Fourth Industrial Revolution unfolding worldwide, technologies including the Internet of Things, sensors, and artificial intelligence are undergoing rapid development. These technological advancements have played a significant role in the dramatic growth of the predictive maintenance market for mechanical equipment, prompting active research on noise removal techniques and classification algorithms for the accurate determination of the causes of equipment failure. In this study, time series data were preprocessed using the denoising autoencoder technique, a deep learning-based noise removal method, to improve the accuracy of failure classification from mechanical equipment data. To convert the preprocessed time series data into frequency components, the short-time Fourier transform technique was employed. The fault types of mechanical equipment were classified using the vision transformer (ViT) technique, a deep learning technique that has been actively used in recent image analysis research. Additionally, the classification performance of the ViT-based technique for vibration time series data was comparatively validated against existing classification algorithms. The accuracy of failure classification was the highest when the data, preprocessed using a Denoising Autoencoder (DAE), were classified by a Vision Transformer (ViT). [ABSTRACT FROM AUTHOR]

Focusing on the classification of business data resources within a unified business semantic environment is an important method to simplify the data environment and a crucial approach to studying data intelligence. A multi-value chain data space is a typical business semantic heterogeneous complex data environment. This paper summarizes the characteristics of multi-value chain business data resources and proposes a study on their classification using business semantic logic. By constructing a semantic-based relational model for multi-value chain business data resources and a multi-value chain business lexicon, this paper unifies the semantics of business data resources. This creates conditions for their classification according to business logic. Based on the feature transformation of business data resources, this paper proposes a clustering algorithm for multi-value chain business data resources (Business data resource classification algorithm for multi-value chain data space, BDRCA4MVCDS) aimed at a data space, completing the classification of business data resources. Finally, comparative experiments with KMeans and KABSA demonstrate the clustering effectiveness of the proposed algorithm (BDRCA4MVCDS) as well as its good stability and adaptability. [ABSTRACT FROM AUTHOR]

Clarifying and differentiating the causes of diseases is an essential step in any clinical activity, but it takes on particular relevance and complexity in the case that arise following vaccinations. The WHO has proposed a protocol that uses a list of specific questions about vaccine-related adverse events and an algorithm for making a judgement. Here, we analyze and discuss the important limitations of this protocol when applied to the new genetic-based anti-COVID-19 vaccines, particularly once dealing with rare and unexpected pathological events. The main controversial aspects concern: (a) the prevailing consideration of other possible causes; (b) the biological plausibility and the choice of an appropriate time window to consider adverse effects possibly caused by vaccines; (c) the reference to scientific literature, which may be very limited and often controversial in early stages of introducing new vaccines because of the short period of observation; (d) the final classification of the algorithm into only three classes, which leaves ample space for the "indeterminate" category. Failure to address these issues may lead to distorted pharmacovigilance reports with significant consequences on the benefit/harm assessment. In anticipation of possible future pandemics managed with new vaccines, the WHO algorithm needs to be revised with appropriate protocols for monitoring and evaluation of adverse effects that take into account the novel mechanism of action and real-world epidemiological data. [ABSTRACT FROM AUTHOR]

Machine-learning algorithms have made significant strides, achieving high accuracy in many applications. However, traditional models often need large datasets, as they typically peel substantial portions of the data in each iteration, complicating the development of a classifier without sufficient data. In critical fields like healthcare, there is a growing need to identify and analyze small yet significant subgroups within data. To address these challenges, we introduce a novel classifier based on the patient rule-induction method (PRIM), a subgroup-discovery algorithm. PRIM finds rules by peeling minimal data at each iteration, enabling the discovery of highly relevant regions. Unlike traditional classifiers, PRIM requires experts to select input spaces manually. Our innovation transforms PRIM into an interpretable classifier by starting with random input space selections for each class, then pruning rules using metarules, and finally selecting definitive rules for the classifier. Tested against popular algorithms such as random forest, logistic regression, and XG-Boost, our random PRIM-based classifier (R-PRIM-Cl) demonstrates comparable robustness, superior interpretability, and the ability to handle categorical and numeric variables. It discovers more rules in certain datasets, making it especially valuable in fields where understanding the model's decision-making process is as important as its predictive accuracy. [ABSTRACT FROM AUTHOR]

Continuous urbanization and climate change degrade urban living conditions. Nature-based solutions in architectural and urban design offer promising remedies but are often hindered by time, cost, and early design phase challenges. To address this, we present a Generative Design System framework utilizing AI-generated images and learning-to-rank algorithms. This system generates numerous image solutions to inspire architects and urban planners, significantly accelerating early design stages. To manage the overwhelming volume of images, we introduce a dilemma-based learning approach that employs learning-to-rank and smart bubble sorting algorithms to prioritize images based on user preference. A case study demonstrates the framework's potential, providing valuable insights into its application, benefits, and limitations in urban design. [ABSTRACT FROM AUTHOR]

For regional desertification control and sustainable development, it is critical to quickly and accurately understand the distribution pattern and spatial and temporal changes of deserts. In this work, five different machine learning algorithms are used to classify different desert types on the Qinghai–Tibetan Plateau (QTP), and their classification performance is evaluated on the basis of their classification results and classification accuracy. Then, on the basis of the best classification model, the Shapely Additive Explanations (SHAP) method is used to clarify the contribution of each classification feature to the identification of desert types during the machine learning classification process, both globally and locally. Finally, the independent and interactive effects of each factor on desert change on the Qinghai-Tibetan Plateau during the study period are quantitatively analyzed via geodetector. The main results are as follows: (1) Compared with other classification algorithms (GTB, CART, KNN, and SVM), the RF classifier achieves the best performance in classifying QTP desert types, with an overall accuracy (OA) of 87.11% and a kappa coefficient of 0.83. (2) From the perspective of the overall classification of deserts, the five features, namely, elevation, slope, VV, VH, and GLCM, contribute most significantly to the features. In terms of the influence of each classification feature on the extraction of different types of deserts, the radar backscattering coefficient VV serves the most important role in distinguishing sandy deserts; the VH is helpful in distinguishing the four types of deserts: rocky desert, alpine cold desert, sandy deserts, and loamy desert; slope is more effective in distinguishing between the two desert types (rocky desert and alpine cold desert) and other types of deserts; and elevation has a significant role in the identification of alpine cold deserts; and the short-wave infrared band SR_B7 has an important role in the identification of salt crusts and saline deserts. (3) During the study period, the QTP deserts exhibited a reversing trend, and the proportion of desert area decreased from 28.62% to 26.20%. (4) Compared with other factors, slope, precipitation, elevation, vegetation type, and the human footprint have greater effects on changes in the QTP desert area, and the interactions among the factors affecting changes in the desert area all show bidirectional enhancement or nonlinear enhancement effects. [ABSTRACT FROM AUTHOR]

This study evaluated the effectiveness of Planet satellite imagery in mapping seagrass coverage in Santa Rosa Sound, Florida. We compared very-high-resolution aerial imagery (0.3 m) collected in September 2022 with high-resolution Planet imagery (~3 m) captured during the same period. Using supervised classification techniques, we accurately identified expansive, continuous seagrass meadows in the satellite images, successfully classifying 95.5% of the 11.18 km2 of seagrass area delineated manually from the aerial imagery. Our analysis utilized an occurrence frequency (OF) product, which was generated by processing ten clear-sky images collected between 8 and 25 September 2022 to determine the frequency with which each pixel was classified as seagrass. Seagrass patches encompassing at least nine pixels (~200 m2) were almost always detected by our classification algorithm. Using an OF threshold equal to or greater than >60% provided a high level of confidence in seagrass presence while effectively reducing the impact of small misclassifications, often of individual pixels, that appeared sporadically in individual images. The image-to-image uncertainty in seagrass retrieval from the satellite images was 0.1 km2 or 2.3%, reflecting the robustness of our classification method and allowing confidence in the accuracy of the seagrass area estimate. The satellite-retrieved leaf area index (LAI) was consistent with previous in situ measurements, leading to the estimate that 2700 tons of carbon per year are produced by the Santa Rosa Sound seagrass ecosystem, equivalent to a drawdown of approximately 10,070 tons of CO2. This satellite-based approach offers a cost-effective, semi-automated, and scalable method of assessing the distribution and abundance of submerged aquatic vegetation that provides numerous ecosystem services. [ABSTRACT FROM AUTHOR]

Mapping pavement types, especially in sidewalks, is essential for urban planning and mobility studies. Identifying pavement materials is a key factor in assessing mobility, such as walkability and wheelchair usability. However, satellite imagery in this scenario is limited, and in situ mapping can be costly. A promising solution is to extract such geospatial features from street-level imagery. This study explores using open-vocabulary classification algorithms to segment and identify pavement types and surface materials in this scenario. Our approach uses large language models (LLMs) to improve the accuracy of classifying different pavement types. The methodology involves two experiments: the first uses free prompting with random street-view images, employing Grounding Dino and SAM algorithms to assess performance across categories. The second experiment evaluates standardized pavement classification using the Deep Pavements dataset and a fine-tuned CLIP algorithm optimized for detecting OSM-compliant pavement categories. The study presents open resources, such as the Deep Pavements dataset and a fine-tuned CLIP-based model, demonstrating a significant improvement in the true positive rate (TPR) from 56.04% to 93.5%. Our findings highlight both the potential and limitations of current open-vocabulary algorithms and emphasize the importance of diverse training datasets. This study advances urban feature mapping by offering a more intuitive and accurate approach to geospatial data extraction, enhancing urban accessibility and mobility mapping. [ABSTRACT FROM AUTHOR]

The characterization and mapping of fuel types is one of the most important factors to consider in the development of accurate fire behavior models. This study introduces a new methodology for generating a fuel map that can be easily updated on an annual basis. The method involves identifying associations between the Moderate Resolution Imaging Spectroradiometer (MODIS) land cover MCD12Q1 classes and the fuel-type classes categorized by the Canadian Fire Behavior Prediction System (FBP). For this purpose, MCD12Q1 Land Cover Type 1 data (MODIS LCM) were collected for the Canadian region. Concurrently, the Canadian fuel-type map implemented in the Fire Behavior Prediction System (FBP FTM) served as the reference dataset. Both MODIS LCM and FBP FTM were reclassified into a new Canadian FTM (NC-FTM) based on seven fuel-type classes. The method involves three key steps: (1) adapting MODIS LCM and FBP FTM for the classification of the Canadian region, (2) removing ambiguity, and (3) characterizing and assessing the accuracy of the new fuel-type classification using a confusion matrix classification algorithm. The achieved accuracy for the new classification exceeds 85%, highlighting the effectiveness of the approach. The use of MODIS LCM offers a cost-effective method for the annual characterization and mapping of fuel types, providing a practical improvement to the FBP model for Canada. Furthermore, with the proposed methodology, a fuel-type map can be generated for other specific areas of interest in the boreal region. [ABSTRACT FROM AUTHOR]

Background: Parkinson's disease (PD) diagnosis benefits significantly from advancements in artificial intelligence (AI) and image processing techniques. This paper explores various approaches for processing hand-drawn Archimedean spirals in order to detect signs of PD. Methods: The best approach is selected to be integrated in a neurodegenerative disease management platform called NeuroPredict. The most innovative aspects of the presented approaches are related to the employed feature extraction techniques that convert hand-drawn spirals into a frequency spectra, so that frequency features may be extracted and utilized as inputs for various classification algorithms. A second category of extracted features contains information related to the thickness and pressure of drawings. Results: The selected approach achieves an overall accuracy of 95.24% and allows acquiring new test data using only a pencil and paper, without requiring a specialized device like a graphic tablet or a digital pen. Conclusions: This study underscores the clinical relevance of AI in enhancing diagnostic precision for neurodegenerative diseases. [ABSTRACT FROM AUTHOR]

The quality of silkworm cocoons affects the quality and cost of silk processing. It is necessary to sort silkworm cocoons prior to silk production. Cocoon images consist of fine-grained images with large intra-class differences and small inter-class differences. The subtle intra-class features pose a serious challenge in accurately locating the effective areas and classifying silkworm cocoons. To improve the perception of intra-class features and the classification accuracy, this paper proposes a bilinear pooling classification model (B-Res41-ASE) based on adaptive multi-scale feature fusion and enhancement. B-Res41-ASE consists of three parts: a feature extraction module, a feature fusion module, and a feature enhancement module. Firstly, the backbone network, ResNet41, is constructed based on the bilinear pooling algorithm to extract complete cocoon features. Secondly, the adaptive spatial feature fusion module (ASFF) is introduced to fuse different semantic information to solve the problem of fine-grained information loss in the process of feature extraction. Finally, the squeeze and excitation module (SE) is used to suppress redundant information, enhance the weight of distinguishable regions, and reduce classification bias. Compared with the widely used classification network, the proposed model achieves the highest classification performance in the test set, with accuracy of 97.0% and an F1-score of 97.5%. The accuracy of B-Res41-ASE is 3.1% and 2.6% higher than that of the classification networks AlexNet and GoogLeNet, respectively, while the F1-score is 2.5% and 2.2% higher, respectively. Additionally, the accuracy of B-Res41-ASE is 1.9% and 7.7% higher than that of the Bilinear CNN and HBP, respectively, while the F1-score is 1.6% and 5.7% higher. The experimental results show that the proposed classification model without complex labelling outperforms other cocoon classification algorithms in terms of classification accuracy and robustness, providing a theoretical basis for the intelligent sorting of silkworm cocoons. [ABSTRACT FROM AUTHOR]

Soluble solids content (SSC) measurements are crucial for managing longan production and post-harvest handling. However, most traditional SSC detection methods are destructive, cumbersome, and unsuitable for field applications. This study proposes a novel field detection model (Brix-back propagation neural network, Brix-BPNN), designed for longan SSC grading based on an improved BP neural network. Initially, nine preprocessing methods were combined with six classification algorithms to develop the longan SSC grading prediction model. Among these, the model preprocessed with Savitzky–Golay smoothing and the first derivative (SG-D1) demonstrated a 7.02% improvement in accuracy compared to the original spectral model. Subsequently, the BP network structure was refined, and the competitive adaptive reweighted sampling (CARS) algorithm was employed for feature wavelength extraction. The results show that the improved Brix-BPNN model, integrated with the CARS, achieves the highest prediction performance, with a 2.84% increase in classification accuracy relative to the original BPNN model. Additionally, the number of wavelengths is reduced by 92% compared to the full spectrum, making this model both lightweight and efficient for rapid field detection. Furthermore, a portable detection device based on visible-near-infrared (Vis-NIR) spectroscopy was developed for longan SSC grading, achieving a prediction accuracy of 83.33% and enabling fast, nondestructive testing in field conditions. [ABSTRACT FROM AUTHOR]

This paper explores the application of Airborne Laser Scanning (ALS) technology in the investigation of the medieval Norman site of Castel Fenuculus, in the lower Calore Valley, Southern Italy. This research aims to assess the actual potential of the ALS dataset provided by the Italian Ministry of the Environment (MATTM) for the detection and visibility of archaeological features in a difficult environment characterised by dense vegetation and morphologically complex terrain. The study focuses on improving the detection and interpretation of archaeological features through a systematic approach that includes the acquisition of ALS point clouds, the implementation of classification algorithms, and the removal of vegetation layers to reveal the underlying terrain and ruined structures. Furthermore, the aim was to test different classification and filtering techniques to identify the best one to use in complex contexts, with the intention of providing a comprehensive and replicable methodological framework. Finally, the Digital Elevation Model (DTM), and various LiDAR-derived models (LDMs), were generated to visualise and highlight topographical features potentially related to archaeological remains. The results obtained demonstrate the significant potential of LiDAR in identifying and documenting archaeological features in densely vegetated and wooded landscapes. [ABSTRACT FROM AUTHOR]

This research presents an unmanned ground vehicle for identifying infested trees by bark beetles in mountain forests. The ground vehicle uses sensors for autonomous navigation and obstacle avoidance. The identification of infested trees is carried out by classifying the resin stains on the bark of unhealthy trees with a computer vision algorithm. This approach proposes tracking bark beetle spread in forest trees with image data of the infested trees considering resin sprouts as early indicators of the infestation in contrast to aerial monitoring, which only detects trees in advanced stages. Terrain autonomous vehicle direction is controlled by changing the velocities of left- and right-side wheels. A rotating LiDAR sensor is used to detect trees and avoid objects. The dynamic model of the vehicle is presented, and a control algorithm is proposed for path-following. Moreover, the stability of the system is proven using a Lyapunov function. In order to demonstrate the performance of the control and classification algorithms, experimental results from an outdoor forest environment are presented. [ABSTRACT FROM AUTHOR]

This study introduces an ensemble model that integrates random forest, gradient boosting, and logistic regression to predict the success of crowdfunding campaigns. Our research develops a novel set of metrics that assess the developmental stage of research projects, facilitating the transition from concept to market-ready product. Utilizing data from multiple sources, including Kaggle's dataset of Kickstarter and Indiegogo projects and a proprietary dataset tailored to our study, the model's performance was evaluated against traditional implementations of random forest and gradient boosting. The results demonstrate the ensemble model's superior performance, achieving an accuracy of 98.94% and an F1 score of 98.81%, significantly outperforming the individual models, showing the best accuracies of around 91% for random forest and lower scores for gradient boosting. This enhancement in predictive power allows for optimized resource allocation and strategic planning in project development, thereby increasing the likelihood of crowdfunding success. This approach streamlines the process of bringing innovative ideas to final products, while at the same time offering a methodologically advanced tool for stakeholders to enhance their campaign strategies effectively. [ABSTRACT FROM AUTHOR]

The classification of red blood cells (RBCs) or erythrocytes into three categories based on their shape, normal, sickle-shaped, and those with other deformations, has proven to be a crucial tool in diagnosing and managing sickle cell disease (SCD). Manual classification techniques have evolved into automated tools, with numerous classification methods being applied based on different ways of representing the cells. In this work, we propose a novel methodology for representing RBCs, defined by selecting k landmarks along the cell boundaries and characterizing shapes as points in the Kendall space of reflection shapes, Ω 2 k . Using this representation, we applied an embedding of the Kendall space Ω 2 k into a Euclidean space, which allowed for the use of machine learning classification algorithms. We also compared our results with those obtained using other classification methods applied to the same dataset in the literature, highlighting the strong performance of our approach in terms of classification accuracy. [ABSTRACT FROM AUTHOR]

The practice of online astroturfing has become increasingly pervasive in recent years, with the growth in popularity of social media. Astroturfing consists of promoting social, political, or other agendas in a non-transparent or deceitful way, where the promoters masquerade as normative users while acting behind a mask that conceals their true identity, and at times that they are not human. In politics, astroturfing is currently considered one of the most severe online threats to democracy. The ability to automatically identify astroturfers thus constitutes a first step in eradicating this threat. We present a complete framework for handling a dataset of profiles, from data collection and efficient labeling, through feature extraction, and finally, to the identification of astroturfers lurking in the dataset. The data were collected over a period of 15 months, during which three consecutive elections were held in Israel. These raw data are unique in scope and size, consisting of several million public comments and reactions to posts on political candidates' pages. For the manual labeling stage, we present a technique that can zoom in on a sufficiently large subset of astroturfer profiles, thus making the procedure highly efficient. The feature extraction stage consists of a temporal layer of features, which proves useful for identifying astroturfers. We then applied and compared several algorithms in the classification stage, and achieved improved results, with an F1 score of 77% and accuracy of 92%. [ABSTRACT FROM AUTHOR]

High noise resistance and high boundary fitting accuracy have always been the goals of image classification. However, the two mutually constrain each other, making it extremely difficult to reach equilibrium. To deal with this problem, the unsupervised image classification algorithm based on fully fuzzy Voronoi tessellation is proposed. It extends Voronoi tessellation from hard to fuzzy, and proposes a hierarchical fuzzy membership model, i.e., pixels fuzzily belong to Voronoi polygons and polygons fuzzily belong to clusters. The objective function is established based on the hierarchical fuzzy membership model by fully considering the transitivity of fuzziness between different levels. Then, the optimal classification result can be obtained by the fuzzy comprehensive decision theory under the best parameter solution. The first level retains the flexibility of pixels while modeling spatial constraints. The second level determines which class the polygon belongs to under the constraint of the first level. It provides an effective way of balancing noise resistance and boundary fitting. In addition, the Voronoi tessellation is explicitly expressed in the objective function in the form of the mathematical model, which allows it to obtain the optimal value through analytical solutions instead of the previous random sampling method. It greatly increases the convergence speed of the algorithm. Experiments have been performed on simulated and several remote sensing images with seven comparing algorithms to demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The objectives of feature selection include simplifying modeling and making the results more understandable, improving data mining efficiency, and providing clean and understandable data preparation. With big data, it also allows us to reduce computational time, improve prediction performance, and better understand the data in machine learning or pattern recognition applications. In this study, we present a new feature selection approach based on hierarchical concept models using formal concept analysis (FCA) and a decision tree (DT) for selecting a subset of attributes. The presented methods are evaluated based on all learned attributes with 10 datasets from the UCI Machine Learning Repository by using three classification algorithms, namely decision trees, support vector machines (SVM), and artificial neural networks (ANN). The hierarchical concept model is built from a dataset, and it is selected by top-down considering features (attributes) node for each level of structure. Moreover, this study is considered to provide a mathematical feature selection approach with optimization based on a paired-samples t-test. To compare the identified models in order to evaluate feature selection effects, the indicators used were information gain (IG) and chi-squared (CS), while both forward selection (FS) and backward elimination (BS) were tested with the datasets to assess whether the presented model was effective in reducing the number of features used. The results show clearly that the proposed models when using DT or using FCA, needed fewer features than the other methods for similar classification performance. [ABSTRACT FROM AUTHOR]

Emotion recognition is critical to understanding students' emotional states. However, problems such as crowded classroom environments, changing light, and occlusion often affect the accuracy of recognition. This study proposes an emotion recognition algorithm specifically for classroom environments. Firstly, the study adds the self-made MCC module and the Wise-IoU loss function to make object detection in the YOLOv8 model more accurate and efficient. Compared with the native YOL0v8x, it reduces the parameters by 16% and accelerates the inference speed by 20%. Secondly, in order to address the intricacies of the classroom setting and the specific requirements of the emotion recognition task, a multi-channel emotion recognition network (MultiEmoNet) has been developed. This network fuses skeletal, environmental, and facial information, and introduces a central loss function and an attention module AAM to enhance the feature extraction capability. The experimental results show that MultiEmoNet achieves a classification accuracy of 91.4% on a homemade classroom student emotion dataset, which is a 10% improvement over the single-channel classification algorithm. In addition, this study also demonstrates the dynamic changes in students' emotions in the classroom through visual analysis, which helps teachers grasp students' emotional states in real time. This paper validates the potential of multi-channel information-fusion deep learning techniques for classroom teaching analysis and provides new ideas and tools for future improvements to emotion recognition techniques. [ABSTRACT FROM AUTHOR]

The reliable operation of power transformers is essential for grid stability, yet existing fault detection methods often suffer from inaccuracies and high false alarm rates. This study introduces a machine learning framework leveraging voltage signals for early fault detection. Simulating diverse fault conditions—including single line-to-ground, line-to-line, turn-to-ground, and turn-to-turn faults—on a laboratory-scale three-phase transformer, we evaluated decision trees, support vector machines, and logistic regression models on a dataset of 6000 samples. Decision trees emerged as the most effective, achieving 99.90% accuracy during 5-fold cross-validation and 95% accuracy on a separate test set of 400 unseen samples. Notably, the framework achieved a low false alarm rate of 0.47% on a separate 6000-sample healthy condition dataset. These results highlight the proposed method's potential to provide a cost-effective, robust, and scalable solution for enhancing transformer fault detection and advancing grid reliability. This demonstrates the efficacy of voltage-based machine learning for transformer diagnostics, offering a practical and resource-efficient alternative to traditional methods. [ABSTRACT FROM AUTHOR]

Inthis paper, a distributed semi-supervised partial multi-label learning (dS2PML) algorithm is proposed, which can be used to address the problem of distributed classification of partially multi-labeled data and unlabeled data. In this algorithm, we utilize the multi-kernel function together with the label correlation term to construct the discriminant function. In addition, to obtain a decentralized implementation, we design a reconstructed error on the labeling confidence based on globally common basic data that are selected by a distributed strategy. By exploiting the similarity structure among feature and label spaces under the sparsity constraint, the labeling confidences of partially multi-labeled and unlabeled data are estimated in a decentralized manner. Meanwhile, by using the sparse random feature map to approximate the kernel feature map, the multi-label classifier can be trained under the supervision of the estimated labeling confidence. Experiments on multiple real datasets are conducted to evaluate the learning performance of the proposed approach. According to the experimental results, the average ranks of all the comparison algorithms evaluated on five evaluation metrics are computed. The ranking results show that the average ranks of our algorithm in terms of hamming loss, one error, average precision, ranking loss, and coverage are 3.16, 2.27, 2.15, 2.38, and 2.18, respectively. The average ranks of the dS2PML are second only to the corresponding centralized S2PML (cS2PML) algorithms and higher than other existing comparison algorithms in five evaluation metrics. The average rank differences in terms of Hamming loss, one error, average precision, ranking loss, and coverage between our proposed algorithm and the closest comparison algorithm are 0.28, 1.67, 1.80, 1.15, and 1.62, respectively. Additionally, owing to the distributed storage and decentralized processing of training data, our proposed dS2PML algorithm reduces CPU time by more than 65% and memory consumption by more than 6% compared to the centralized comparison algorithms. The experimental results indicate that our proposed algorithm outperforms the other state-of-the-art algorithms in classification accuracy, CPU time, and memory consumption. [ABSTRACT FROM AUTHOR]

In this work, we studied the use of Quantum Machine Learning (QML) algorithms for binary classification and compared their performance with classical Machine Learning (ML) methods. QML merges principles of Quantum Computing (QC) and ML, offering improved efficiency and potential quantum advantage in data-driven tasks and when solving complex problems. In binary classification, where the goal is to assign data to one of two categories, QML uses quantum algorithms to process large datasets efficiently. Quantum algorithms like Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) exploit quantum parallelism and entanglement to enhance performance over classical methods. This study focuses on two common QML algorithms, Quantum Support Vector Classifier (QSVC) and QNN. We used the Qiskit software and conducted the experiments with three different datasets. Data preprocessing included dimensionality reduction using Principal Component Analysis (PCA) and standardization using scalers. The results showed that quantum algorithms demonstrated competitive performance against their classical counterparts in terms of accuracy, while QSVC performed better than QNN. These findings suggest that QML holds potential for improving computational efficiency in binary classification tasks. This opens the way for more efficient and scalable solutions in complex classification challenges and shows the complementary role of quantum computing. [ABSTRACT FROM AUTHOR]

The aim of this study was to explore the application of computational models for the analysis of histopathological images in the context of colon cancer. A comprehensive dataset of colon cancer images annotated into eight distinct categories based on their representation of cancerous cell portions was used. The primary objective was to employ various image classification algorithms to assess their efficacy in the context of cancer classification. Additionally, this study investigated the use of feature extraction techniques to derive meaningful data from the images, contributing to a more nuanced understanding of cancerous tissues, comparing the performance of different image classification algorithms in the context of colon cancer image analysis. The findings of this research suggested that XGboost provides the highest accuracy (89.79%) and could contribute to the growing body of knowledge in computational pathology. Other algorithms, such as the random forest, SVM, and CNN, also provided satisfactory results, offering insights into the effectiveness of image classification algorithms in distinguishing between different categories of cancerous cells. This work holds implications for the development of more accurate and efficient tools, underscoring the potential of computational models in enhancing the analysis of histopathological images and improving diagnostic capabilities in cancer research. [ABSTRACT FROM AUTHOR]

In this study, we addressed the difficulty of systematic and accurate identification and early warning of secondary disaster events after natural disasters. We analyzed the causes of common secondary disaster events, established the correlation between common everyday items and the types of secondary disasters, and constructed six secondary disaster factor datasets, namely, fire, flammable objects, explosive objects, toxic substances, trapped personnel, and dangerous buildings. We proposed a multi-model cluster decision method to extract the secondary disaster factors' visual features, and we created a ResNet-CDMV image classification algorithm with higher accuracy recognition performance than the traditional single model. The experimental results show that the ResNet-CDMV algorithm in this study has an identification mAP value of 87% for secondary disaster factors. For this algorithm, Faster-RCNN, SSD, CornerNet, and CenterNet, the mAP value of the YOLOv7 object detection algorithm is increased by 9.333%, 11.833%, 13%, 11%, and 8.167%, respectively. Based on the systematic analysis of the formation mechanism of secondary disasters, the high-precision identification method built in this study is applied to the identification and early warning of secondary disasters, which is of great significance in reducing the occurrence of secondary disasters and ensuring the protection of life and property. [ABSTRACT FROM AUTHOR]

This article presents a discussion of the application of machine learning methods to enhance the quality of drive shaft production, with a particular focus on the identification of critical quality issues, including cracks, scratches, and dimensional deviations, which have been observed in the final stages of machining. A variety of classification algorithms, including neural networks (NNs), bagged trees (BT), and support vector machines (SVMs), were employed to efficiently analyse and predict defects. The results show that neural networks achieved the highest accuracy (94.7%) and the fastest prediction time, thereby underscoring their efficiency in processing complex production data. The BT model demonstrated stability in its predictions with a slower prediction time, while the SVM model exhibited superior training speed, though with slightly lower accuracy. This article proposes that optimising key process parameters, such as temperature, machining speed, and the type of coolant used, can markedly reduce the prevalence of production defects. It also recommends integrating machine learning with traditional quality management techniques to create a more flexible and adaptive control system, which could help reduce production losses and enhance customer satisfaction. [ABSTRACT FROM AUTHOR]

5G positioning technology has become deeply integrated into daily life. However, in wireless signal propagation environments, there may exist non-line-of-sight (NLOS) conditions, which lead to signal blockage and subsequently hinder the provision of positioning services. To address this issue, this paper proposes an intelligent reflecting surface (IRS) NLOS time difference of arrival–angle of arrival (TDOA-AOA) localization (INTAL) algorithm. First, the algorithm constructs a system model for 5G IRS localization, effectively overcoming the challenges of positioning in NLOS paths. Then, by applying the multiple signal classification algorithm to estimate the time delay and angle, and using the Chan algorithm to obtain the user's estimated coordinates, an optimization problem is formulated to minimize the distance between the estimated and actual coordinates. The tent–snake optimization algorithm is employed to solve this optimization problem, thereby reducing localization errors. Finally, simulations demonstrate that the INTAL algorithm outperforms the snake optimization (SO) algorithm and the gray wolf optimization (GWO) algorithm under the same conditions, reducing the localization error by 56% and 60% on average, respectively. Additionally, when the signal-to-noise ratio is 30 dB, the localization error of the INTAL algorithm is only 0.2968 m, while the errors for the SO and GWO algorithms are 0.6733 m and 0.7398 m, respectively. This further proves the significant improvement of the algorithm in terms of localization accuracy. [ABSTRACT FROM AUTHOR]

In data science and machine learning, efficient and scalable algorithms are paramount for handling large datasets and complex tasks. Classification algorithms, in particular, play a crucial role in a wide range of applications, from image recognition and natural language processing to fraud detection and medical diagnosis. Traditional classification methods, while effective, often struggle with scalability and efficiency when applied to massive datasets. This challenge has driven the development of innovative approaches that leverage modern computational frameworks and parallel processing capabilities. This paper presents the Bison Algorithm, applied to classification problems. The algorithm, inspired by the social behavior of bison, aims to enhance the accuracy of classification tasks. The Bison Algorithm is implemented using PySpark, leveraging the distributed computing power to handle large datasets efficiently. This study compares the performance of the Bison Algorithm on several dataset sizes using speedup and scaleup as the performance measure. [ABSTRACT FROM AUTHOR]

This study aimed to explore the potential of predicting diabetes by analyzing trends in plantar thermal and plantar pressure data, either individually or in combination, using various machine learning techniques. A total of twenty-six participants, comprising thirteen individuals diagnosed with diabetes and thirteen healthy individuals, walked along a 20 m path. In-shoe plantar pressure data were collected and the plantar temperature was measured both immediately before and after the walk. Each participant completed the trial three times, and the average data between the trials were calculated. The research was divided into three experiments: the first evaluated the correlations between the plantar pressure and temperature data; the second focused on predicting diabetes using each data type independently; and the third combined both data types and assessed the effect of such to enhance the predictive accuracy. For the experiments, 20 regression models and 16 classification algorithms were employed, and the performance was evaluated using a five-fold cross-validation strategy. The outcomes of the initial set of experiments indicated that the machine learning models were significant correlations between the thermal data and pressure estimates. This was consistent with the findings from the prior correlation analysis, which showed weak relationships between these two data modalities. However, a shift in focus towards predicting diabetes by aggregating the temperature and pressure data led to encouraging results, demonstrating the effectiveness of this approach in accurately predicting the presence of diabetes. The analysis revealed that, while several classifiers demonstrated reasonable metrics when using standalone variables, the integration of thermal and pressure data significantly improved the predictive accuracy. Specifically, when only plantar pressure data were used, the Logistic Regression model achieved the highest accuracy at 68.75%. Those predictions based solely on temperature data showed the Naive Bayes model as the lead with an accuracy of 87.5%. Notably, the highest accuracy of 93.75% was observed when both the temperature and pressure data were combined, with the Extra Trees Classifier performing the best. These results suggest that combining temperature and pressure data enhances the model's predictive accuracy. This can indicate the importance of multimodal data integration and their potentials in diabetes prediction. [ABSTRACT FROM AUTHOR]

The presence of gray mold can seriously affect the yield and quality of strawberries. Due to their susceptibility and the rapid spread of this disease, it is important to develop early, accurate, rapid, and non-destructive disease identification strategies. In this study, the early detection of strawberry leaf diseases was performed using hyperspectral imaging combining multi-dimensional features like spectral fingerprints and vegetation indices. Firstly, hyperspectral images of healthy and early affected leaves (24 h) were acquired using a hyperspectral imaging system. Then, spectral reflectance (616) and vegetation index (40) were extracted. Next, the CARS algorithm was used to extract spectral fingerprint features (17). Pearson correlation analysis combined with the SPA method was used to select five significant vegetation indices. Finally, we used five deep learning methods (LSTMs, CNNs, BPFs, and KNNs) to build disease detection models for strawberries based on individual and fusion characteristics. The results showed that the accuracy of the recognition model based on fused features ranged from 88.9% to 96.6%. The CNN recognition model based on fused features performed best, with a recognition accuracy of 96.6%. Overall, the fused feature-based model can reduce the dimensionality of the classification data and effectively improve the predicting accuracy and precision of the classification algorithm. [ABSTRACT FROM AUTHOR]

Malware detection, targeting the microarchitecture of processors, has recently come to light as a potentially effective way to improve computer system security. Hardware Performance Counter data are used by machine learning algorithms in security mechanisms, such as hardware-based malware detection, to categorize and detect malware. It is crucial to determine whether or not a file contains malware. Many issues have been brought about by the rise in malware, and businesses are losing vital data and dealing with other issues. The second thing to keep in mind is that malware can quickly cause a lot of damage to a system by slowing it down and encrypting a large amount of data on a personal computer. This study provides extensive details on a flexible framework related to machine learning and deep learning techniques using few-shot learning. Malware detection is possible using DT, RF, LR, SVM, and FSL techniques. The logic is that these algorithms make it simple to differentiate between files that are malware-free and those that are not. This indicates that their goal is to reduce the number of false positives in the data. For this, we use two different datasets from an online platform. In this research work, we mainly focus on few-shot learning techniques by using two different datasets. The proposed model has an 97% accuracy rate, which is much greater than that of other techniques. [ABSTRACT FROM AUTHOR]

Since Kraljic's strategic matrix was applied to supply chain management, classification of items, suppliers, and customers has become of increasing interest to research and companies. The aim of this research is to develop an easily interpretable multicriteria classification matrix method and validate it in real-world scenarios with a robustness analysis. This method assigns alternatives to one of four classes defined by critical dimensions that integrate several evaluation criteria. Initially, a global search pre-classifies the alternatives using the PROMETHEE net flows. Then, two local searches are carried out that make use of the discriminant properties of the net flow signs to improve the quality of the assignments. This approach is specifically applied to pre-classified alternatives near the boundary between two or more categories. The method has been validated by segmenting thousands of customers. Four customer segments were identified: strategic, collaborative, transactional, and non-preferred. A comparison was made between the results and those derived from an alternative method. Through an extensive sensitivity analysis, the proposed method was shown to be robust to parameter variation, highlighting its reliability in real dynamic contexts. The method provides valuable, easily interpretable information, which constitutes the basis for developing personalised strategies to enhance customer relationship management. [ABSTRACT FROM AUTHOR]

The availability of reliable and quantified information on the spatiotemporal distribution of irrigated land at the river basin scale is an essential step towards sustainable management of water resources. This research aims to assess the spatiotemporal extent of irrigated land in the Ouémé River basin using Landsat multi-temporal images and ground truth data. A methodology was built around the use of supervised classification and the application of an algorithm based on the logical expression and thresholding of a combination of surface temperature (Ts) and normalized difference vegetation index (NDVI). The findings of the supervised classification showed that agricultural areas were 16,003 km2, 19,732 km2, and 22,850 km2 for the years 2014, 2018, and 2022, respectively. The irrigated land areas were 755 km2, 1143 km2, and 1883 km2 for the same years, respectively. A significant increase in irrigated areas was recorded throughout the study period. The overall accuracy values of 79%, 82%, and 83% obtained during validation of the irrigated land maps indicate a good performance of the algorithm. The results suggest a promising application of the algorithm to obtain up-to-date information on the distribution of irrigated land in several regions of Africa. [ABSTRACT FROM AUTHOR]

Lower limb exoskeletons have been developed to improve functionality and assist with daily activities in various environments. Although these systems utilize sensors for gait phase detection, they lack anticipatory information about environmental changes, which limits their adaptability. This paper presents a vision-based intelligent gait environment detection algorithm for a lightweight ankle exosuit designed to enhance gait stability and safety for stroke patients, particularly during stair negotiation. The proposed system employs YOLOv8 for real-time environment classification, combined with a long short-term memory (LSTM) network for spatio-temporal feature extraction, enabling the precise detection of environmental transitions. An experimental study evaluated the classification algorithm and soft ankle exosuit performance through three conditions using kinematic analysis and muscle activation measurements. The algorithm achieved an overall accuracy of over 95% per class, which significantly enhanced the exosuit's ability to detect environmental changes, and thereby improved its responsiveness to various conditions. Notably, the exosuit increased the ankle dorsiflexion angles and reduced the muscle activation during the stair ascent, which enhanced the foot clearance. The results of this study indicate that advanced spatio-temporal feature analysis and environment classification improve the exoskeleton's gait assistance, improving adaptability in complex environments for stroke patients. [ABSTRACT FROM AUTHOR]

This paper introduces an advanced acoustic imaging system leveraging multibeam water column data at various frequencies to detect and classify marine litter. This study encompasses (i) the acquisition of test tank data for diverse types of marine litter at multiple acoustic frequencies; (ii) the creation of a comprehensive acoustic image dataset with meticulous labelling and formatting; (iii) the implementation of sophisticated classification algorithms, namely support vector machine (SVM) and convolutional neural network (CNN), alongside cutting-edge detection algorithms based on transfer learning, including single-shot multibox detector (SSD) and You Only Look once (YOLO), specifically YOLOv8. The findings reveal discrimination between different classes of marine litter across the implemented algorithms for both detection and classification. Furthermore, cross-frequency studies were conducted to assess model generalisation, evaluating the performance of models trained on one acoustic frequency when tested with acoustic images based on different frequencies. This approach underscores the potential of multibeam data in the detection and classification of marine litter in the water column, paving the way for developing novel research methods in real-life environments. [ABSTRACT FROM AUTHOR]

Estimating the completion cost accurately in the early phases of construction projects is critical to their success. However, cost overruns are almost inevitable due to the risks inherent in construction projects. Hence, the completion cost fluctuates throughout the execution phase and requires periodic updates. There is a need for a prompt and user-friendly completion cost estimation model that accounts for fluctuating risk scores and their impacts on the total cost during the execution phase. Machine learning (ML) techniques could address these requirements by providing effective methods for tackling dynamic systems. The proposed approach aims to predict the cost overrun ratio classes of the completion cost according to the changes in the total risk scores at any time of the project. Six classification algorithms were utilized and validated by employing 110 data points from a globally operating construction company. The performances of the algorithms were evaluated with validation and performance indices. The decision tree classifier surpassed other algorithms. Although there are some research limitations, including risk perception, data gathering restrictions, and selecting proper ML algorithms upon data properties, this research improves the planning abilities of construction executives by providing a cost overrun ratio based on changing total risk scores, facilitating swift and simple assessments at any stage of a construction project's execution. [ABSTRACT FROM AUTHOR]

Compared to traditional technology, image classification technology possesses a superior capability for quantitative analysis of the target and background, and holds significant applications in the domains of ground target reconnaissance, marine environment monitoring, and emergency response to sudden natural disasters, among others. Currently, the enhancement of spatial spectral resolution heightens the difficulty and reduces the efficiency of classification, posing a substantial challenge to the aforementioned applications. Hence, the classification algorithm is required to take both computing power and classification accuracy into account. Research indicates that the deep kernel mapping network can accommodate both computing power and classification accuracy. By employing the kernel mapping function as the network node function of deep learning, it effectively enhances the classification accuracy under the condition of limited computing power. Therefore, to address the issue of network structure optimization of deep mapping networks and the insufficient application of line feature learning and expression in existing network structures, considering the adaptive optimization of network structures, deep quasiconformal kernel network learning (DQKNet) is proposed for image classification. Firstly, the structural parameters and learning parameters of the deep kernel mapping network are optimized. This approach can adaptively adjust the network structure based on the distribution characteristics of the data and enhance the performance of image classification. Secondly, the computational network node optimization method of quasiconformal kernel learning is applied to this network, further elevating the performance of the deep kernel learning mapping network in image classification. The experimental results demonstrate that the improvement in the deep kernel mapping network from the perspectives of accounting children, mapping network nodes, and network structure can effectively enhance the feature extraction and classification performance of the data. On the five public datasets, the average AA, OA, and KC values of our algorithm are 91.99, 91.25, and 85.99, respectively, outperforming the currently most-advanced algorithms. [ABSTRACT FROM AUTHOR]