PeerJ Computer Science最新文献

{"title":"A study of trust mining algorithms for beacon nodes in large-scale network environments.","authors":"Yanyan Jiang","doi":"10.7717/peerj-cs.2755","DOIUrl":"https://doi.org/10.7717/peerj-cs.2755","url":null,"abstract":"<p><p>In a large-scale network environment, node positioning is prone to large deviations. Mining beacon node trust is the basis for precise node positioning in the network environment. Therefore, this article studies the trust degree mining algorithm of beacon nodes in a large-scale network environment. First, according to the distance error evaluation and probability function of beacon nodes in the large-scale network environment, the direct trust degree of beacon nodes is obtained. The trust degree is converted into influence, and the influence of beacon nodes is mined using the seepage theory to determine the beacon node with the highest impact in the large-scale network environment. Then, according to the influence of nodes, received signal strength indicator (RSSI) is used to optimize the conventional distance vector hop (DV-Hop) node location algorithm. The influence weights the average hop distance of beacon nodes. The weight of the influence of beacon nodes defines the average hop distance of unknown nodes. The average hop distance information of unknown nodes is taken from more high-influence beacon nodes, solving the problem of significant positioning errors caused by the uncertainty of location targets. Finally, the security status of nodes is reflected according to the degree of trust of different nodes to beacon nodes. The experimental results show that the algorithm can accurately locate other nodes in a wide network environment when the number of beacon nodes and communication distance change, and the trust degree of nodes mined can accurately reflect the security status of nodes.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2755"},"PeriodicalIF":3.5,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190256/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Epileptic seizures diagnosis and prognosis from EEG signals using heterogeneous graph neural network.","authors":"Areej Alasiry, Gabriel Avelino Sampedro, Ahmad Almadhor, Roben A Juanatas, Shtwai Alsubai, Vincent Karovic","doi":"10.7717/peerj-cs.2765","DOIUrl":"10.7717/peerj-cs.2765","url":null,"abstract":"<p><p>Epilepsy, often associated with neurodegenerative disorders following brain strokes, manifests as abnormal electrical activity bursts in the cerebral cortex, disrupting regular brain function. Electroencephalogram (EEG) recordings capture these distinctive brain signals, offering crucial insights into seizure detection and management. This study presents a novel approach leveraging a graph neural network (GNN) model with a heterogeneous graph representation to detect epileptic seizures from EEG data. Utilizing the well-established CHB-MIT EEG dataset for training and evaluation, the proposed method includes preprocessing steps such as signal segmentation, resampling, label encoding, normalization, and exploratory data analysis. We employed a standard train-test split with stratified sampling to ensure class distribution and reduce bias. Experimental comparisons with long short-term memory (LSTM) and recurrent neural network (RNN) models highlight the GNN's superior performance, achieving a classification accuracy of 98.0% and demonstrating incremental improvements in precision and F1-score. These findings emphasize the efficacy of GNN in capturing spatial and temporal dependencies within EEG data, surpassing conventional deep learning techniques. Furthermore, the study highlights the model's interpretability, which is essential for clinical decision-making. By advancing EEG-based seizure prediction methods, this research offers a robust framework for enhancing patient outcomes in epilepsy management while addressing the limitations of existing approaches.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2765"},"PeriodicalIF":3.5,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190335/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting no-shows at outpatient appointments in internal medicine using machine learning models.","authors":"Felipe Ocampo Osorio, Santiago Pedroza Gomez, David Esteban Rebellón Sanchez, Richard Ramirez Fernandez, Reinel Tabares-Soto, Mario Alejandro Bravo-Ortíz, Gustavo Adolfo Cruz Suarez","doi":"10.7717/peerj-cs.2762","DOIUrl":"10.7717/peerj-cs.2762","url":null,"abstract":"<p><p>The high prevalence of patient absenteeism in medical appointments poses significant challenges for healthcare providers and patients, causing delays in service delivery and increasing operational inefficiencies. Addressing this issue is crucial in the internal medicine department, a fundamental pillar of comprehensive adult healthcare that manages various chronic and complex conditions. To mitigate absenteeism, we present an innovative application of machine learning models specifically designed to predict the risk of patient absenteeism in the internal medicine department of Fundación Valle del Lili, a high-complexity hospital in Colombia. Leveraging an institutional database, we conducted a statistical analysis to identify critical variables influencing absenteeism risk, including clinical and sociodemographic factors and characteristics of previously attended appointments. Our study evaluated seven distinct machine learning models, explored various data processing techniques, and addressed class imbalance through oversampling and undersampling strategies. Hyperparameter optimization was conducted for each model configuration, culminating in selecting the Bagging RandomForest model, which demonstrated outstanding performance when combined with standardized data and balanced using the Synthetic Minority Oversampling Technique (SMOTE). Additionally, Shapley values (SHAP) were applied to enhance the interpretability of the model, enabling the identification of the most influential variables in predicting medical absenteeism, such as the number of previous absences, the day and month of the appointment, and diagnosed diseases. The selected model achieved a predictive accuracy of 84.80 ± 0.81%, an AUC value of 0.89, an F1-score of 84.75%, and a recall of 83.02% in cross-validation experiments. These results highlight the potential of our experimental approach to identify the most suitable model for proactively predicting patients at high risk of absenteeism, optimizing resource allocation, and improving the quality of medical care in internal medicine in the future. Our methodology provides a foundation for reducing operational inefficiencies and strengthening intervention strategies. This benefits healthcare providers and patients through more timely and effective care. Ultimately, this approach contributes to improving patient outcomes and institutional efficiency.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2762"},"PeriodicalIF":3.5,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel user-centric happiness model for personalized tour recommendations.","authors":"Mohammed Alatiyyah","doi":"10.7717/peerj-cs.2837","DOIUrl":"10.7717/peerj-cs.2837","url":null,"abstract":"<p><p>A novel personalized tour recommendation model, the Happiness Model (HM), is presented. The HM optimizes itineraries by considering traveler satisfaction as a function of time and maximizing it over the trip duration. The model integrates the Item Constraints Data Model (ICDM) to reduce data dimensionality and search space. By considering various activities within different points of interest (POIs) and minimizing wasted time, the HM overcomes the limitations of existing methods. Unlike existing POI-centric models, the HM is time-centric, creating tour recommendations that maximize user satisfaction throughout the trip. Experimental results demonstrate the model's effectiveness in generating personalized tour recommendations aligned with user preferences. The HM achieves an average satisfaction score of 0.85 across multiple datasets, outperforming traditional models such as the Time-Dependent Orienteering Problem with Time Windows (TOPTW), which achieves an average score of 0.72. Additionally, the HM reduces waiting times by 30% and increases the number of recommended POIs by 20% compared to existing methods. These results highlight the HM's ability to provide more efficient and enjoyable travel experiences.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2837"},"PeriodicalIF":3.5,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192884/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting sarcasm in user-generated content integrating transformers and gated graph neural networks.","authors":"Zhenkai Qin, Qining Luo, Zhidong Zang, Hongpeng Fu","doi":"10.7717/peerj-cs.2817","DOIUrl":"10.7717/peerj-cs.2817","url":null,"abstract":"<p><p>The widespread use of the Internet and social media has posed significant challenges to automated sentiment analysis, particularly in relation to detecting sarcasm in user-generated content. Sarcasm often expresses negative emotions through seemingly positive or exaggerated language, making its detection a complex task in natural language processing. To address this issue, the present study proposes a novel sarcasm detection model that combines bidirectional encoder representations from transformers (BERT) with gated graph neural networks (GGNN), further enhanced by a self-attention mechanism to more effectively capture ironic cues. BERT is utilized to extract deep contextual information from the text, while GGNN is employed to learn global semantic structures by incorporating dependency and emotion graphs. Experiments were conducted on two benchmark sarcasm detection datasets, namely Headlines and Riloff. The experimental results demonstrate that the proposed BERT-GGNN model achieves an accuracy of 92.00% and an F1 score of 91.51% on the Headlines dataset, as well as an accuracy of 86.49% and an F1 score of 86.59% on the Riloff dataset, significantly outperforming the conventional BERT-GCN models. The results of ablation studies further corroborate the efficacy of integrating GGNN, particularly for handling complex ironic expressions frequently encountered in social media contexts.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2817"},"PeriodicalIF":3.5,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190390/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards efficient glaucoma screening with modular convolution-involution cascade architecture.","authors":"Mohamed Mouhafid, Yatong Zhou, Chunyan Shan, Zhitao Xiao","doi":"10.7717/peerj-cs.2844","DOIUrl":"10.7717/peerj-cs.2844","url":null,"abstract":"<p><p>Automated glaucoma detection from retinal fundus images plays a crucial role in facilitating early intervention and improving the management of this progressive ocular condition. Although convolutional neural networks (CNNs) have significantly advanced image analysis, current CNN-based models encounter two major limitations. First, they rely primarily on convolutional operations, which restrict the ability to capture cross-channel correlations effectively due to the channel-specific focus of these operations. Second, they often depend on fully-connected (FC) layers for classification, which can introduce unnecessary complexity and limit adaptability, potentially impacting overall classification performance. This study introduces the Modular Convolution-Involution Cascade Network (MCICNet), an innovative CNN architecture designed to address these challenges in the context of glaucoma detection. The model employs a combination of convolution and involution operations in a cascade structure, allowing for the effective capture of inter-channel dependencies within the feature extraction process. Furthermore, the classification phase integrates light gradient boosting machine (LightGBM) as a replacement for traditional FC layers, offering enhanced precision and generalization while reducing model complexity. Extensive experiments conducted on the LAG and ACRIMA datasets demonstrate that MCICNet achieves significant improvements compared to existing CNN and transformer-based models. The model attained a classification accuracy of 95.6% on the LAG dataset and 96.2% on ACRIMA, outperforming nine widely used CNN architectures (AlexNet, MobileNetV2, SqueezeNet, ResNet18, GoogLeNet, DenseNet121, EfficientNetB0, ShuffleNet, and VGG16), as well as three transformer-based models (ViT, MaxViT, and SwinT). Additionally, MCICNet showed superior performance over its variant without involution (MCICNet-NoInvolution). With only 0.9 million parameters, MCICNet demonstrates substantial efficiency in resource utilization alongside its high learning capability, establishing it as an advanced and computationally efficient solution for glaucoma detection.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2844"},"PeriodicalIF":3.5,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192679/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companies.","authors":"Walaa Gamaleldin, Osama Attayyib, Mrim M Alnfiai, Faiz Abdullah Alotaibi, Ruixing Ming","doi":"10.7717/peerj-cs.2830","DOIUrl":"10.7717/peerj-cs.2830","url":null,"abstract":"<p><p>This article proposes a hybrid model to assist insurance companies accurately assess the risk of increasing claims for their premiums. The model integrates long short-term memory (LSTM) networks and convolutional neural networks (CNN) to analyze historical claim data and identify emerging risk trends. We analyzed data obtained from insurance companies and found that the hybrid CNN-LSTM model outperforms standalone models in accurately assessing and categorizing risk levels. The proposed CNN-LSTM model achieved an accuracy of 98.5%, outperforming the standalone CNN (95.8%) and LSTM (92.6%). We implemented 10-fold cross-validation to ensure robustness, confirming consistent performance across different data splits. Furthermore, we validated the model on an external dataset to assess its generalizability. The results demonstrate that the model effectively classifies insurance risks in different market environments, highlighting its potential for real-world applications. Our study contributes to the insurance industry by providing valuable insights for effective risk management strategies and highlights the model's broader applicability in global insurance markets.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2830"},"PeriodicalIF":3.5,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190450/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unbiased machine learning-assisted approach for conditional discretization of human performances.","authors":"Thepparit Banditwattanawong, Masawee Masdisornchote","doi":"10.7717/peerj-cs.2804","DOIUrl":"https://doi.org/10.7717/peerj-cs.2804","url":null,"abstract":"<p><p>Performance discretization maps numerical performance values to ordinal categories or performance ranking labels. Norm-referenced performance discretization is extensively applied in human performance evaluation such as grading academic achievements and determining salary increases for employees. These tasks stipulate a common condition that certain performance ranking labels might have no associated performance values and are referred to as conditional discretization. Currently, the only statistical method available for norm-referenced performance discretization is Z score, which merely addresses partial conditions. To achieve a fully conditionally norm-referenced performance discretization, this article proposes four novel approaches enlisting a multi-modal technique that incorporates unsupervised machine-learning algorithms and a heuristic method as well as a novel decision function ensuring conditional unbiasedness. The machine-learning-based methods demonstrate superiority over the heuristic one across most testing data sets, achieving a conditional unbiasedness degree ranging from 0.11 to 0.82. On the other hand, the heuristic method notably outperforms for a specific data set, exhibiting a conditional unbiasedness degree up to 0.76. Leveraging the strengths of these constituent methods enable the effectiveness of the proposed multi-modal approach for conditionally norm-referenced performance discretization.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2804"},"PeriodicalIF":3.5,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190627/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Building extraction from remote sensing images based on multi-scale attention gate and enhanced positional information.","authors":"Rui Xu, Renzhong Mao, Zhenxing Zhuang, Fenghua Huang, Yihui Yang","doi":"10.7717/peerj-cs.2826","DOIUrl":"10.7717/peerj-cs.2826","url":null,"abstract":"<p><p>Extracting buildings from high-resolution remote sensing images is currently a research hotspot in the field of remote sensing applications. Deep learning methods have significantly improved the accuracy of building extraction, but there are still deficiencies such as blurred edges, incomplete structures and loss of details in the extraction results. To obtain accurate contours and clear boundaries of buildings, this article proposes a novel building extraction method utilizing multi-scale attention gate and enhanced positional information. By employing U-Net as the main framework, this article introduces a multi-scale attention gate module in the encoder, which effectively improves the ability to capture multi-scale information, and designs a module in the decoder to enhance the positional information of the features, allowing for more precise localization and extraction of the shape and edge information of buildings. To validate the effectiveness of the proposed method, comprehensive evaluations were conducted on three benchmark datasets, Massachusetts, WHU, and Inria. The comparative analysis with six state-of-the-art models (SegNet, DeepLabv3+, U-Net, DSATNet, SDSC-Unet, and BuildFormer) demonstrates consistent performance improvements in intersection over union (IoU) metrics. Specifically, the proposed method achieves IoU increments of 2.19%, 3.31%, 3.10%, 2.00%, 3.35%, and 3.48% respectively on Massachusetts dataset, 1.26%, 4.18%, 1.18%, 2.01%, 2.03%, and 2.29% on WHU dataset, and 0.87%, 5.25%, 2.02%, 5.55%, 4.39%, and 1.18% on Inria dataset. The experimental results indicate that the proposed method can effectively integrate multi-scale features and optimize the extracted building edges, achieving superior performance compared to existing methodologies in building extraction tasks.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2826"},"PeriodicalIF":3.5,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190511/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FLASC: a flare-sensitive clustering algorithm.","authors":"Daniël M Bot, Jannes Peeters, Jori Liesenborgs, Jan Aerts","doi":"10.7717/peerj-cs.2792","DOIUrl":"10.7717/peerj-cs.2792","url":null,"abstract":"<p><p>Exploratory data analysis workflows often use clustering algorithms to find groups of similar data points. The shape of these clusters can provide meaningful information about the data. For example, a Y-shaped cluster might represent an evolving process with two distinct outcomes. This article presents flare-sensitive clustering (FLASC), an algorithm that detects branches within clusters to identify such shape-based subgroups. FLASC builds upon HDBSCAN*-a state-of-the-art density-based clustering algorithm-and detects branches in a post-processing step using within-cluster connectivity. Two algorithm variants are presented, which trade computational cost for noise robustness. We show that both variants scale similarly to HDBSCAN* regarding computational cost and provide similar outputs across repeated runs. In addition, we demonstrate the benefit of branch detection on two real-world data sets. Our implementation is included in the <i>hdbscan</i> Python package and available as a standalone package at https://github.com/vda-lab/pyflasc.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2792"},"PeriodicalIF":3.5,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190649/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}