PeerJ Computer Science最新文献

Background: In recent years, artificial intelligence (AI) and deep learning (DL) have made a considerable impact in dentistry, specifically in advancing image processing algorithms for detecting caries from radiographical images. Despite this progress, there is still a lack of data on the effectiveness of these algorithms in accurately identifying caries. This study provides an overview aimed at evaluating and comparing reviews that focus on the detection of dental caries (DC) using DL algorithms from 2D radiographs.

Materials and methods: This comprehensive umbrella review adhered to the "Reporting guideline for overviews of reviews of healthcare interventions" (PRIOR). Specific keywords were generated to assess the accuracy of AI and DL algorithms in detecting DC from radiographical images. To ensure the highest quality of research, thorough searches were performed on PubMed/Medline, Web of Science, Scopus, and Embase. Additionally, bias in the selected articles was rigorously assessed using the Joanna Briggs Institute (JBI) tool.

Results: In this umbrella review, seven systematic reviews (SRs) were assessed from a total of 77 studies included. Various DL algorithms were used across these studies, with conventional neural networks and other techniques being the predominant methods for detecting DC. The SRs included in the study examined 24 original articles that used 2D radiographical images for caries detection. Accuracy rates varied between 0.733 and 0.986 across datasets ranging in size from 15 to 2,500 images.

Conclusion: The advancement of DL algorithms in detecting and predicting DC through radiographic imaging is a significant breakthrough. These algorithms excel in extracting subtle features from radiographic images and applying machine learning techniques to achieve highly accurate predictions, often outperforming human experts. This advancement holds immense potential to transform diagnostic processes in dentistry, promising to considerably improve patient outcomes.

With the continued development of information technology and increased global cultural exchanges, translation has gained significant attention. Traditional manual translation relies heavily on dictionaries or personal experience, translating word by word. While this method ensures high translation quality, it is often too slow to meet the demands of today's fast-paced environment. Computer-assisted translation (CAT) addresses the issue of slow translation speed; however, the quality of CAT translations still requires rigorous evaluation. This study aims to answer the following questions: How do CAT systems that use automated programming fare compared to more conventional methods of human translation when translating English vocabulary? (2) How can CAT systems be improved to handle difficult English words, specialised terminology, and semantic subtleties? The working premise is that CAT systems that use automated programming techniques will outperform traditional methods in terms of translation accuracy. English vocabulary plays a crucial role in translation, as words can have different meanings depending on the context. CAT systems improve their translation accuracy by utilising specific automated programs and building a translation corpus through translation memory technology. This study compares the accuracy of English vocabulary translations produced by CAT based on automatic programming with those produced by traditional manual translation. Experimental results demonstrate that CAT based on automatic programming is 8% more accurate than traditional manual translation when dealing with complex English vocabulary sentences, professional jargon, English acronyms, and semantic nuances. Consequently, compared to conventional human translation, CAT can enhance the accuracy of English vocabulary translation, making it a valuable tool in the translation industry.

Radio frequency interference disrupts services offered by Global Navigation Satellite Systems (GNSS). Spoofing is the transmission of structured interference signals intended to deceive GNSS location and timing services. The identification of spoofing is vital, especially for safety-of-life aviation services, since the receiver is unaware of counterfeit signals. Although numerous spoofing detection and mitigation techniques have been developed, spoofing attacks are becoming more sophisticated, limiting most of these methods. This study explores the application of machine learning techniques for discerning authentic signals from counterfeit ones. The investigation particularly focuses on the secure code estimation and replay (SCER) spoofing attack, one of the most challenging type of spoofing attacks, ds8 scenario of the Texas Spoofing Test Battery (TEXBAT) dataset. The proposed framework uses tracking data from delay lock loop correlators as intrinsic features to train four distinct machine learning (ML) models: logistic regression, support vector machines (SVM) classifier, K-nearest neighbors (KNN), and decision tree. The models are trained employing a random six-fold cross-validation methodology. It can be observed that both logistic regression and SVM can detect spoofing with a mean F1-score of 94%. However, logistic regression provides 165dB gain in terms of time efficiency as compared to SVM and 3 better than decision tree-based classifier. These performance metrics as well as receiver operating characteristic curve analysis make logistic regression the desirable approach for identifying SCER structured interference.

Background: The Zika virus (ZIKV), which is transmitted by mosquito vectors to nonhuman primates and humans, causes devastating outbreaks in the poorest tropical regions of the world. Molecular epidemiology, supported by clustering phylogenetic gold standard studies using sequence data, has provided valuable information for tracking and controlling the spread of ZIKV. Unsupervised learning (UL), a form of machine learning algorithm, can be applied on the datasets without the need of known information for training.

Methods: In this work, unsupervised Random Forest (URF), followed by the application of dimensional reduction algorithms such as principal component analysis (PCA), Uniform Manifold Approximation and Projection (UMAP), t-distributed stochastic neighbor embedding (t-SNE), and autoencoders were used to uncover hidden patterns from polymorphic amino acid sites extracted on the proteome ZIKV multi-alignments, without the need of an underlying evolutionary model.

Results: The four UL algorithms revealed specific host and geographical clustering patterns for ZIKV. Among the four dimensionality reduction (DR) algorithms, the performance was better for UMAP. The four algorithms allowed the identification of imported viruses for specific geographical clusters. The UL dimension coordinates showed a significant correlation with phylogenetic tree branch lengths and significant phylogenetic dependence in Abouheif's Cmean and Pagel's Lambda tests (p value < 0.01) that showed comparable performance with the phylogenetic method. This analytical strategy was generalizable to an external large dengue type 2 dataset.

Conclusion: These UL algorithms could be practical evolutionary analytical techniques to track the dispersal of viral pathogens.

Labor force participation of Egyptian women has been a chronic economic problem in Egypt. Despite the improvement in the human capital front, whether on the education or health indicators, female labor force participation remains persistently low. This study proposes a hybrid machine-learning model that integrates principal component analysis (PCA) for feature extraction with various machine learning and time-series models to predict women's employment in times of crisis. Various machine learning (ML) algorithms, such as support vector machine (SVM), neural network, K-nearest neighbor (KNN), linear regression, random forest, and AdaBoost, in addition to popular time series algorithms, including autoregressive integrated moving average (ARIMA) and vector autoregressive (VAR) models, have been applied to an actual dataset from the public sector. The manpower dataset considered gender from different regions, ages, and educational levels. The dataset was then trained, tested, and evaluated. For performance validation, forecasting accuracy metrics were constructed using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), R-squared (R2), and cross-validated root mean squared error (CVRMSE). Another Dickey-Fuller test was performed to evaluate and compare the accuracy of the applied models, and the results showed that AdaBoost outperforms the other methods by an accuracy of 100%. Compared to alternative works, our findings demonstrate a comprehensive comparative analysis for predicting women's participation in different regions during an economic crisis.

This article addresses the problem of interval pricing for auction items by constructing an auction item price prediction model based on an adaptive learning algorithm. Firstly, considering the confusing class characteristics of auction item prices, a dynamic inter-class distance adaptive learning model is developed to identify confusing classes by calculating the differences in prediction values across multiple classifiers for target domain samples. The difference in the predicted values of the target domain samples on multiple classifiers is used to calculate the classification distance, distinguish the confusing classes, and make the similar samples in the target domain more clustered. Secondly, a deep clustering algorithm is constructed, which integrates the temporal characteristics and numerical differences of auction item prices, using DTW-K-medoids based dynamic time warping (DTW) and fuzzy C-means (FCM) algorithms for fine clustering. Finally, the KF-LSTM auction item interval price prediction model is constructed using long short-term memory (LSTM) and dual clustering. Experimental results show that the proposed KF-LSTM model significantly improves the prediction accuracy of auction item prices during fluctuation periods, with an average accuracy rate of 90.23% and an average MAPE of only 5.41%. Additionally, under confidence levels of 80%, 85%, and 90%, the KF-LSTM model achieves an interval coverage rate of over 85% for actual auction item prices, significantly enhancing the accuracy of auction item price predictions. This experiment demonstrates the stability and accuracy of the proposed model when applied to different sets of auction items, providing a valuable reference for research in the auction item price prediction field.

Despite the identification of several dozen genetic loci associated with ischemic stroke (IS), the genetic bases of this disease remain largely unexplored. In this research we present the results of genome-wide association studies (GWAS) based on classical statistical testing and machine learning algorithms (logistic regression, gradient boosting on decision trees, and tabular deep learning model TabNet). To build a consensus on the results obtained by different techniques, the Pareto-Optimal solution was proposed and applied. These methods were applied to real genotypic data of sick and healthy individuals of European ancestry obtained from the Database of Genotypes and Phenotypes (5,581 individuals, 883,749 single nucleotide polymorphisms). Finally, 131 genes were identified as candidates for association with the onset of IS. UBQLN1, TRPS1, and MUSK were previously described as associated with the course of IS in model animals. ACOT11 taking part in metabolism of fatty acids was shown for the first time to be associated with IS. The identified genes were compared with genes from the Illuminating Druggable Genome project. The product of GPR26 representing the G-coupled protein receptor can be considered as a therapeutic target for stroke prevention. The approaches presented in this research can be used to reprocess GWAS datasets from other diseases.

This article aims to develop a novel Artificial Intelligence-powered Internet of Things (AI-powered IoT) system that can automatically monitor the conditions of the plant (crop) and apply the necessary action without human interaction. The system can remotely send a report on the plant conditions to the farmers through IoT, enabling them for tracking the healthiness of plants. Chili plant has been selected to test the proposed AI-powered IoT monitoring and actuating system as it is so sensitive to the soil moisture, weather changes and can be attacked by several types of diseases. The structure of the proposed system is passed through five main stages, namely, AI-powered IoT system design, prototype fabrication, signal and image processing, noise elimination and proposed system testing. The prototype for monitoring is equipped with multiple sensors, namely, soil moisture, carbon dioxide (CO₂) detector, temperature, and camera sensors, which are utilized to continuously monitor the conditions of the plant. Several signal and image processing operations have been applied on the acquired sensors data to prepare them for further post-processing stage. In the post processing step, a new AI based noise elimination algorithm has been introduced to eliminate the noise in the images and take the right actions which are performed using actuators such as pumps, fans to make the necessary actions. The experimental results show that the prototype is functioning well with the proposed AI-powered IoT algorithm, where the water pump, exhausted fan and pesticide pump are actuated when the sensors detect a low moisture level, high CO₂ concentration level, and video processing-based pests' detection, respectively. The results also show that the algorithm is capable to detect the pests on the leaves with 75% successful rate.

Positive and unlabeled (PU) learning is a type of semi-supervised binary classification where the machine learning algorithm differentiates between a set of positive instances (labeled) and a set of both positive and negative instances (unlabeled). PU learning has broad applications in settings where confirmed negatives are unavailable or difficult to obtain, and there is value in discovering positives among the unlabeled (e.g., viable drugs among untested compounds). Most PU learning algorithms make the selected completely at random (SCAR) assumption, namely that positives are selected independently of their features. However, in many real-world applications, such as healthcare, positives are not SCAR (e.g., severe cases are more likely to be diagnosed), leading to a poor estimate of the proportion, α, of positives among unlabeled examples and poor model calibration, resulting in an uncertain decision threshold for selecting positives. PU learning algorithms vary; some estimate only the proportion, α, of positives in the unlabeled set, while others calculate the probability that each specific unlabeled instance is positive, and some can do both. We propose two PU learning algorithms to estimate α, calculate calibrated probabilities for PU instances, and improve classification metrics: i) PULSCAR (positive unlabeled learning selected completely at random), and ii) PULSNAR (positive unlabeled learning selected not at random). PULSNAR employs a divide-and-conquer approach to cluster SNAR positives into subtypes and estimates α for each subtype by applying PULSCAR to positives from each cluster and all unlabeled. In our experiments, PULSNAR outperformed state-of-the-art approaches on both synthetic and real-world benchmark datasets.

Mobile app reviews are valuable for gaining user feedback on features, usability, and areas for improvement. Analyzing these reviews manually is difficult due to volume and structure, leading to the need for automated techniques. This mapping study categorizes existing approaches for automated and semi-automated tools by analyzing 180 primary studies. Techniques include topic modeling, collocation finding, association rule-based, aspect-based sentiment analysis, frequency-based, word vector-based, and hybrid approaches. The study compares various tools for analyzing mobile app reviews based on performance, scalability, and user-friendliness. Tools like KEFE, MERIT, DIVER, SAFER, SIRA, T-FEX, RE-BERT, and AOBTM outperformed baseline tools like IDEA and SAFE in identifying emerging issues and extracting relevant information. The study also discusses limitations such as manual intervention, linguistic complexities, scalability issues, and interpretability challenges in incorporating user feedback. Overall, this mapping study outlines the current state of feature extraction from app reviews, suggesting future research and innovation opportunities for extracting software requirements from mobile app reviews, thereby improving mobile app development.