PeerJ Computer Science最新文献

{"title":"Classification of sleep apnea syndrome using the spectrograms of EEG signals and YOLOv8 deep learning model.","authors":"Kubra Tanci, Mahmut Hekim","doi":"10.7717/peerj-cs.2718","DOIUrl":"10.7717/peerj-cs.2718","url":null,"abstract":"<p><p>In this study, we focus on classifying sleep apnea syndrome by using the spectrograms obtained from electroencephalogram (EEG) signals taken from polysomnography (PSG) recordings and the You Only Look Once (YOLO) v8 deep learning model. For this aim, the spectrograms of segments obtained from EEG signals with different apnea-hypopnea values (AHI) using a 30-s window function are obtained by short-time Fourier transform (STFT). The spectrograms are used as inputs to the YOLOv8 model to classify sleep apnea syndrome as mild, moderate, severe apnea, and healthy. For four-class classification models, the standard reference level is 25%, assuming equal probabilities for all classes or an equal number of samples in each class. In this context, this information is an important reference point for the validity of our study. Deep learning methods are frequently used for the classification of EEG signals. Although ResNet64 and YOLOv5 give effective results, YOLOv8 stands out with fast processing times and high accuracy. In the existing literature, parameter reduction approaches in four-class EEG classification have not been adequately addressed and there are limitations in this area. This study evaluates the performance of parameter reduction methods in EEG classification using YOLOv8, fills gaps in the existing literature for four-class classification, and reduces the number of parameters of the used models. Studies in the literature have generally classified sleep apnea syndrome as binary (apnea/healthy) and ignored distinctions between apnea severity levels. Furthermore, most of the existing studies have used models with a high number of parameters and have been computationally demanding. In this study, on the other hand, the use of spectrograms is proposed to obtain higher correct classification ratios by using more accurate and faster models. The same classification experiments are reimplemented for widely used ResNet64 and YOLOv5 deep learning models to compare with the success of the proposed model. In the implemented experiments, total correct classification (TCC) ratios are 93.7%, 93%, and 88.2% for YOLOv8, ResNet64, and YOLOv5, respectively. These experiments show that the YOLOv8 model reaches higher success ratios than the ResNet64 and YOLOv5 models. Although the TCC ratios of the YOLOv8 and ResNet64 models are comparable, the YOLOv8 model uses fewer parameters and layers than the others, providing a faster processing time and a higher TCC ratio. The findings of the study make a significant contribution to the current state of the art. As a result, this study gives rise to the idea that the YOLOv8 deep learning model can be used as a new tool for classification of sleep apnea syndrome from EEG signals.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2718"},"PeriodicalIF":3.5,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888935/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588330","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":"GATI-RS model using Bi-LSTM and multi-head attention mechanism to enhance online shopping experience for the elderly with accurate click-through rate prediction.","authors":"Ying Liu, Shahriman Zainal Abidin, Verly Veto Vermol, Shaolong Yang, Hanyu Liu","doi":"10.7717/peerj-cs.2707","DOIUrl":"10.7717/peerj-cs.2707","url":null,"abstract":"<p><p>With the rapid development of e-commerce and the increasing aging population, more elderly people are engaging in online shopping. However, challenges they face during this process are becoming more apparent. This article proposes a recommendation system based on click-through rate (CTR) prediction, aiming to enhance the online shopping experience for elderly users. By analyzing user characteristics, product features, and their interactions, we constructed a model combining bidirectional long short-term memory (Bi-LSTM) and multi-head self-attention mechanism to predict the item click behavior of elderly users in the recommendation section. Experimental results demonstrated that the model excels in CTR prediction, effectively improving the relevance of recommended content. Compared to the baseline model long short-term memory (LSTM), the GATI-RS framework improved CTR prediction accuracy by 40%, and its loss function rapidly decreased and remained stable during training. Additionally, the GATI-RS framework showed significant performance improvement when considering only elderly users, with accuracy surpassing the baseline model by 42%. These results indicate that the GATI-RS framework, through optimized algorithms, significantly enhances the model's global information integration and complex pattern recognition capabilities, providing strong support for developing recommendation systems for elderly online shoppers. This research not only offers new insights for e-commerce platforms to optimize services but also contributes to improving the quality of life and well-being of the elderly.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2707"},"PeriodicalIF":3.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888906/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588114","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":"BiLSTM-enhanced legal text extraction model using fuzzy logic and metaphor recognition.","authors":"Jia Chen","doi":"10.7717/peerj-cs.2697","DOIUrl":"10.7717/peerj-cs.2697","url":null,"abstract":"<p><p>The burgeoning field of natural language processing (NLP) has witnessed exponential growth, captivating researchers due to its diverse practical applications across industries. However, the intricate nature of legal texts poses unique challenges for conventional text extraction methods. To surmount these challenges, this article introduces a pioneering legal text extraction model rooted in fuzzy language processing and metaphor recognition, tailored for the domain of online environment governance. Central to this model is the utilization of a bidirectional long short-term memory (Bi-LSTM) network, adept at delineating illicit behaviors by establishing connections between legal provisions and judgments. Additionally, a self-attention module is integrated into the Bi-LSTM architecture, augmented by L2 regularization, to facilitate the efficient extraction of legal text information, thereby enabling the identification and classification of illegal content. This innovative approach effectively resolves the issue of legal text recognition. Experimental findings underscore the efficacy of the proposed method, achieving an impressive macro-F1 score of 0.8005, precision of 0.8047, and recall of 0.8014. Furthermore, the article delves into an analysis and discussion of the potential application prospects of the legal text extraction model, grounded in fuzzy language processing and metaphor recognition, within the realm of online environment governance.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2697"},"PeriodicalIF":3.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888925/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588302","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":"Tuck-KGC: based on tensor decomposition for diabetes knowledge graph completion model integrating Chinese and Western medicine.","authors":"Jiangtao ZhangSun, Yu Xin Yang, Beiji Zou, Qinghua Peng, Xiao Xia Xiao","doi":"10.7717/peerj-cs.2522","DOIUrl":"10.7717/peerj-cs.2522","url":null,"abstract":"<p><p>The medical knowledge graph is essential for intelligent medical services, encompassing personalized diagnostics, precision therapies, and intelligent consultations, among others. However, medical knowledge graphs frequently suffer from incompleteness, primarily due to the absence of certain entities or relationships. The incomplete nature of knowledge graphs poses substantial challenges to these tasks. Knowledge graph completion technology is instrumental in addressing this issue. Specifically, tensor decomposition-based approaches for knowledge graph completion embed entities and relationships into the vector space, where tensor decomposition computations are employed to predict missing relationships within the knowledge graph. However, the tensor representation of entities and their relationships often overlooks crucial entity type information, potentially resulting in an abundance of irrational relationships during the prediction process. To mitigate this, we propose the Tucker Decomposition Knowledge Graph Completion (Tuck-KGC) method, which incorporates entity types into the tensor decomposition framework. This method maps the types of medical entities to vectors, which are seamlessly integrated into the knowledge graph representation learning process. This allows the model to thoroughly absorb entity information, thereby enhancing the accuracy of link prediction. To evaluate the Tuck-KGC, we built the Dia dataset, a knowledge graph tailored for precision medical analysis, which integrates both Traditional Chinese Medicine and Western medicine perspectives. The Dia dataset encompasses 10,294 entities with 214 relationships, covering a comprehensive spectrum including diseases, treatments, clinical manifestations, complications, etiology, and so on. Building upon the Dia dataset, experimental results indicate that the Tuck-KGC model boosts link prediction accuracy by roughly 8%, affirming the efficacy of incorporating entity type information into the model.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2522"},"PeriodicalIF":3.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888843/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588120","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":"Leveraging sentiment analysis of food delivery services reviews using deep learning and word embedding.","authors":"Dheya Mustafa, Safaa M Khabour, Mousa Al-Kfairy, Ahmed Shatnawi","doi":"10.7717/peerj-cs.2669","DOIUrl":"10.7717/peerj-cs.2669","url":null,"abstract":"<p><p>Companies that deliver food (food delivery services, or FDS) try to use customer feedback to identify aspects where the customer experience could be improved. Consumer feedback on purchasing and receiving goods <i>via</i> online platforms is a crucial tool for learning about a company's performance. Many English-language studies have been conducted on sentiment analysis (SA). Arabic is becoming one of the most extensively written languages on the World Wide Web, but because of its morphological and grammatical difficulty as well as the lack of openly accessible resources for Arabic SA, like as dictionaries and datasets, there has not been much research done on the language. Using a manually annotated FDS dataset, the current study conducts extensive sentiment analysis using reviews related to FDS that include Modern Standard Arabic and dialectal Arabic. It does this by utilizing word embedding models, deep learning techniques, and natural language processing to extract subjective opinions, determine polarity, and recognize customers' feelings in the FDS domain. Convolutional neural network (CNN), bidirectional long short-term memory recurrent neural network (BiLSTM), and an LSTM-CNN hybrid model were among the deep learning approaches to classification that we evaluated. In addition, the article investigated different effective approaches for word embedding and stemming techniques. Using a dataset of Modern Standard Arabic and dialectal Arabic <i>corpus</i> gathered from Talabat.com, we trained and evaluated our suggested models. Our best accuracy was approximately 84% for multiclass classification and 92.5% for binary classification on the FDS. To verify that the proposed approach is suitable for analyzing human perceptions in diversified domains, we designed and carried out excessive experiments on other existing Arabic datasets. The highest obtained multi-classification accuracy is 88.9% on the Hotels Arabic-Reviews Dataset (HARD) dataset, and the highest obtained binary classification accuracy is 97.2% on the same dataset.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2669"},"PeriodicalIF":3.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888876/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588210","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":"Diagnostic test accuracy of AI-assisted mammography for breast imaging: a narrative review.","authors":"Daksh Dave, Adnan Akhunzada, Nikola Ivković, Sujan Gyawali, Korhan Cengiz, Adeel Ahmed, Ahmad Sami Al-Shamayleh","doi":"10.7717/peerj-cs.2476","DOIUrl":"10.7717/peerj-cs.2476","url":null,"abstract":"<p><p>The integration of artificial intelligence into healthcare, particularly in mammography, holds immense potential for improving breast cancer diagnosis. Artificial intelligence (AI), with its ability to process vast amounts of data and detect intricate patterns, offers a solution to the limitations of traditional mammography, including missed diagnoses and false positives. This review focuses on the diagnostic accuracy of AI-assisted mammography, synthesizing findings from studies across different clinical settings and algorithms. The motivation for this research lies in addressing the need for enhanced diagnostic tools in breast cancer screening, where early detection can significantly impact patient outcomes. Although AI models have shown promising improvements in sensitivity and specificity, challenges such as algorithmic bias, interpretability, and the generalizability of models across diverse populations remain. The review concludes that while AI holds transformative potential in breast cancer screening, collaborative efforts between radiologists, AI developers, and policymakers are crucial for ensuring ethical, reliable, and inclusive integration into clinical practice.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2476"},"PeriodicalIF":3.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888881/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588003","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":"The technique of fuzzy analytic hierarchy process (FAHP) based on the triangular q-rung fuzzy numbers (TR-q-ROFNS) with applications in best African coffee brand selection.","authors":"Yupei Huang, Muhammad Gulistan, Amir Rafique, Wathek Chammam, Khursheed Aurangzeb, Ateeq Ur Rehman","doi":"10.7717/peerj-cs.2555","DOIUrl":"10.7717/peerj-cs.2555","url":null,"abstract":"<p><p>The African coffee market offers a rich and diverse range of coffee profiles. The coffee producers of Africa face numerous challenges like climate change, market fluctuations, diseases, soil degradation and limited access to finance. These challenges badly affect their productivity, quality and livelihood. There are different factors like social and cultural, which can affect the coffee production. This study aims to develop multi criteria decision making (MCDM) methods and their applications in coffee market specifically in identifying factors influencing consumers' coffee brand preferences in South Africa, which is known for its vibrant coffee culture. For this purpose, first we developed the technique of analytic hierarchy process (AHP) in the environment of triangular q-rung orthopair fuzzy numbers. The triangular q-rung fuzzy numbers can effectively handle the uncertainity. The AHP technique has widely been used in decision making due to its flexibility in assigning weights and dealing with vagueness. The weights of critera plays a very important role in an MCDM problem. The development of AHP technique in triangular q-rung orthopair fuzzy environment can improve the decision making (DM) by handling vagueness in data and by using the most appropriate weights. Furthermore this new proposed method improves accuracy and minimize the information loss. The newly peoposed method is applied to different MCDM problems and comparative analysis is conducted to check the validity of results.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2555"},"PeriodicalIF":3.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888883/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588118","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":"Optimizing power allocation for URLLC-D2D in 5G networks with Rician fading channel.","authors":"Owais Muhammad, Hong Jiang, Muhammad Bilal, Mushtaq Muhammad Umer","doi":"10.7717/peerj-cs.2712","DOIUrl":"10.7717/peerj-cs.2712","url":null,"abstract":"<p><p>The rapid evolution of wireless technologies within the 5G network brings significant challenges in managing the increased connectivity and traffic of mobile devices. This enhanced connectivity brings challenges for base stations, which must handle increased traffic and efficiently serve a growing number of mobile devices. One of the key solutions to address these challenges is integrating device-to-device (D2D) communication with ultra-reliable and low-latency communication (URLLC). This study examines the impact of the Rician fading channel on the performance of D2D communication under URLLC. It addresses the critical problem of optimizing power allocation to maximize the minimum data rate in D2D communication. A significant challenge arises due to interference issues, as the problem of maximizing the minimum data rate is non-convex, which leads to high computational complexity. This complexity makes it difficult to derive optimal solutions efficiently. To address this challenge, we introduce an algorithm that is based on derivatives to find the optimal power allocation. Comparisons are made with the branch and bound (B&B) algorithm, heuristic algorithm, and particle swarm optimization (PSO) algorithm. Our proposed algorithm improves power allocation performance and also achieves faster execution with lower computational complexity compared to the B&B, PSO, and heuristic algorithms.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2712"},"PeriodicalIF":3.5,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888938/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588198","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":"Enhancing fraud detection in the Ethereum blockchain using ensemble learning.","authors":"Zhexian Gu, Omar Dib","doi":"10.7717/peerj-cs.2716","DOIUrl":"10.7717/peerj-cs.2716","url":null,"abstract":"<p><p>The Ethereum blockchain operates as a decentralized platform, utilizing blockchain technology to distribute smart contracts across a global network. It enables currency and digital value exchange without centralized control. However, the exponential growth of online commerce has created a fertile ground for a surge in fraudulent activities such as money laundering and phishing, thereby exacerbating significant security vulnerabilities. To combat this, our article introduces an ensemble learning approach to accurately detect fraudulent Ethereum blockchain transactions. Our goal is to integrate a decision-making tool into the decentralized validation process of Ethereum, allowing blockchain miners to identify and flag fraudulent transactions. Additionally, our system can assist governmental organizations in overseeing the blockchain network and identifying fraudulent activities. Our framework incorporates various data pre-processing techniques and evaluates multiple machine learning algorithms, including logistic regression, Isolation Forest, support vector machine, Random Forest, XGBoost, and recurrent neural network. These models are fine-tuned using grid search to enhance their performance. The proposed approach utilizes an ensemble of three distinct models (Random Forest, extreme gradient boosting (XGBoost), and support vector machine) to further improve classification performance. It achieves high scores of over 98% across key classification metrics like accuracy, precision, recall, and F1-score. Moreover, the approach is suitable for real-world usage, with an inference time of 0.13 s.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2716"},"PeriodicalIF":3.5,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888915/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588088","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":"Stock market trading <i>via</i> actor-critic reinforcement learning and adaptable data structure.","authors":"Cesar Guevara","doi":"10.7717/peerj-cs.2690","DOIUrl":"10.7717/peerj-cs.2690","url":null,"abstract":"<p><p>Currently, the stock market is attractive, and it is challenging to develop an efficient investment model with high accuracy due to changes in the values of the shares for political, economic, and social reasons. This article presents an innovative proposal for a short-term, automatic investment model to reduce capital loss during trading, applying a reinforcement learning (RL) model. On the other hand, we propose an adaptable data window structure to enhance the learning and accuracy of investment agents in three foreign exchange markets: crude oil, gold, and the Euro. In addition, the RL model employs an actor-critic neural network with rectified linear unit (ReLU) neurons to generate specialized investment agents, enabling more efficient trading, minimizing investment losses across different time periods, and reducing the model's learning time. The proposed RL model obtained a reduction average loss of 0.03% in Euro, 0.25% in gold, and 0.13% in crude oil in the test phase with varying initial conditions.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2690"},"PeriodicalIF":3.5,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888913/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588188","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}