Electroencephalography (EEG) is a medical engineering technique aimed at recording the electric activity of the human brain. Brain signals derived from an EEG device can be processed and analyzed through computers by using digital signal processing, computational statistics, and machine learning techniques, that can lead to scientifically-relevant results and outcomes about how the brain works. In the last decades, the spread of EEG devices and the higher availability of EEG data, of computational resources, and of software packages for electroencephalography analysis has made EEG signal processing easier and faster to perform for any researcher worldwide. This increased ease to carry out computational analyses of EEG data, however, has made it easier to make mistakes, as well. And these mistakes, if unnoticed or treated wrongly, can in turn lead to wrong results or misleading outcomes, with worrisome consequences for patients and for the advancements of the knowledge about human brain. To tackle this problem, we present here our ten quick tips to perform electroencephalography signal processing analyses avoiding common mistakes: a short list of guidelines designed for beginners on what to do, how to do it, and what not to do when analyzing EEG data with a computer. We believe that following our quick recommendations can lead to better, more reliable and more robust results and outcome in clinical neuroscientific research.
{"title":"Ten quick tips for clinical electroencephalographic (EEG) data acquisition and signal processing","authors":"Giulia Cisotto, Davide Chicco","doi":"10.7717/peerj-cs.2256","DOIUrl":"https://doi.org/10.7717/peerj-cs.2256","url":null,"abstract":"Electroencephalography (EEG) is a medical engineering technique aimed at recording the electric activity of the human brain. Brain signals derived from an EEG device can be processed and analyzed through computers by using digital signal processing, computational statistics, and machine learning techniques, that can lead to scientifically-relevant results and outcomes about how the brain works. In the last decades, the spread of EEG devices and the higher availability of EEG data, of computational resources, and of software packages for electroencephalography analysis has made EEG signal processing easier and faster to perform for any researcher worldwide. This increased ease to carry out computational analyses of EEG data, however, has made it easier to make mistakes, as well. And these mistakes, if unnoticed or treated wrongly, can in turn lead to wrong results or misleading outcomes, with worrisome consequences for patients and for the advancements of the knowledge about human brain. To tackle this problem, we present here our ten quick tips to perform electroencephalography signal processing analyses avoiding common mistakes: a short list of guidelines designed for beginners on what to do, how to do it, and what not to do when analyzing EEG data with a computer. We believe that following our quick recommendations can lead to better, more reliable and more robust results and outcome in clinical neuroscientific research.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"27 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Davide Chicco, Angeliki-Ilektra Karaiskou, Maarten De Vos
The electrocardiogram (ECG) is a powerful tool to measure the electrical activity of the heart, and the analysis of its data can be useful to assess the patient’s health. In particular, the computational analysis of electrocardiogram data, also called ECG signal processing, can reveal specific patterns or heart cycle trends which otherwise would be unnoticeable by medical experts. When performing ECG signal processing, however, it is easy to make mistakes and generate inflated, overoptimistic, or misleading results, which can lead to wrong diagnoses or prognoses and, in turn, could even contribute to bad medical decisions, damaging the health of the patient. Therefore, to avoid common mistakes and bad practices, we present here ten easy guidelines to follow when analyzing electrocardiogram data computationally. Our ten recommendations, written in a simple way, can be useful to anyone performing a computational study based on ECG data and eventually lead to better, more robust medical results.
{"title":"Ten quick tips for electrocardiogram (ECG) signal processing","authors":"Davide Chicco, Angeliki-Ilektra Karaiskou, Maarten De Vos","doi":"10.7717/peerj-cs.2295","DOIUrl":"https://doi.org/10.7717/peerj-cs.2295","url":null,"abstract":"The electrocardiogram (ECG) is a powerful tool to measure the electrical activity of the heart, and the analysis of its data can be useful to assess the patient’s health. In particular, the computational analysis of electrocardiogram data, also called ECG signal processing, can reveal specific patterns or heart cycle trends which otherwise would be unnoticeable by medical experts. When performing ECG signal processing, however, it is easy to make mistakes and generate inflated, overoptimistic, or misleading results, which can lead to wrong diagnoses or prognoses and, in turn, could even contribute to bad medical decisions, damaging the health of the patient. Therefore, to avoid common mistakes and bad practices, we present here ten easy guidelines to follow when analyzing electrocardiogram data computationally. Our ten recommendations, written in a simple way, can be useful to anyone performing a computational study based on ECG data and eventually lead to better, more robust medical results.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"24 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yibo Han, Meiting Lin, Ni Li, Qi Qi, Jinqing Li, Qingxin Liu
Particle swarm optimization (PSO) stands as a prominent and robust meta-heuristic algorithm within swarm intelligence (SI). It originated in 1995 by simulating the foraging behavior of bird flocks. In recent years, numerous PSO variants have been proposed to address various optimization applications. However, the overall performance of these variants has not been deemed satisfactory. This article introduces a novel PSO variant, presenting three key contributions: First, a novel dynamic oscillation inertia weight is introduced to strike a balance between exploration and exploitation; Second, the utilization of cosine similarity and dynamic neighborhood strategy enhances both the quality of solution and the diversity of particle populations; Third, a unique worst-best example learning strategy is proposed to enhance the quality of the least favorable solution and consequently improving the overall population. The algorithm’s validation is conducted using a test suite comprised of benchmarks from the CEC2014 and CEC2022 test suites on real-parameter single-objective optimization. The experimental results demonstrate the competitiveness of our algorithm against recently proposed state-of-the-art PSO variants and well-known algorithms.
{"title":"DCWPSO: particle swarm optimization with dynamic inertia weight updating and enhanced learning strategies","authors":"Yibo Han, Meiting Lin, Ni Li, Qi Qi, Jinqing Li, Qingxin Liu","doi":"10.7717/peerj-cs.2253","DOIUrl":"https://doi.org/10.7717/peerj-cs.2253","url":null,"abstract":"Particle swarm optimization (PSO) stands as a prominent and robust meta-heuristic algorithm within swarm intelligence (SI). It originated in 1995 by simulating the foraging behavior of bird flocks. In recent years, numerous PSO variants have been proposed to address various optimization applications. However, the overall performance of these variants has not been deemed satisfactory. This article introduces a novel PSO variant, presenting three key contributions: First, a novel dynamic oscillation inertia weight is introduced to strike a balance between exploration and exploitation; Second, the utilization of cosine similarity and dynamic neighborhood strategy enhances both the quality of solution and the diversity of particle populations; Third, a unique worst-best example learning strategy is proposed to enhance the quality of the least favorable solution and consequently improving the overall population. The algorithm’s validation is conducted using a test suite comprised of benchmarks from the CEC2014 and CEC2022 test suites on real-parameter single-objective optimization. The experimental results demonstrate the competitiveness of our algorithm against recently proposed state-of-the-art PSO variants and well-known algorithms.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"2 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shanza Zafar Malik, Khalid Iqbal, Muhammad Sharif, Yaser Ali Shah, Amaad Khalil, M. Abeer Irfan, Joanna Rosak-Szyrocka
Automatic polarity prediction is a challenging assessment issue. Even though polarity assessment is a critical topic with many existing applications, it is probably not an easy challenge and faces several difficulties in natural language processing (NLP). Public polling data can give useful information, and polarity assessment or classification of comments on Twitter and Facebook may be an effective approach for gaining a better understanding of user sentiments. Text embedding techniques and models related to the artificial intelligence field and sub-fields with differing and almost accurate parameters are among the approaches available for assessing student comments. Existing state-of-the-art methodologies for sentiment analysis to analyze student responses were discussed in this study endeavor. An innovative hybrid model is proposed that uses ensemble learning-based text embedding, a multi-head attention mechanism, and a combination of deep learning classifiers. The proposed model outperforms the existing state-of-the-art deep learning-based techniques. The proposed model achieves 95% accuracy, 97% recall, having a precision of 95% with an F1-score of 96% demonstrating its effectiveness in sentiment analysis of student feedback.
{"title":"Attention-aware with stacked embedding for sentiment analysis of student feedback through deep learning techniques","authors":"Shanza Zafar Malik, Khalid Iqbal, Muhammad Sharif, Yaser Ali Shah, Amaad Khalil, M. Abeer Irfan, Joanna Rosak-Szyrocka","doi":"10.7717/peerj-cs.2283","DOIUrl":"https://doi.org/10.7717/peerj-cs.2283","url":null,"abstract":"Automatic polarity prediction is a challenging assessment issue. Even though polarity assessment is a critical topic with many existing applications, it is probably not an easy challenge and faces several difficulties in natural language processing (NLP). Public polling data can give useful information, and polarity assessment or classification of comments on Twitter and Facebook may be an effective approach for gaining a better understanding of user sentiments. Text embedding techniques and models related to the artificial intelligence field and sub-fields with differing and almost accurate parameters are among the approaches available for assessing student comments. Existing state-of-the-art methodologies for sentiment analysis to analyze student responses were discussed in this study endeavor. An innovative hybrid model is proposed that uses ensemble learning-based text embedding, a multi-head attention mechanism, and a combination of deep learning classifiers. The proposed model outperforms the existing state-of-the-art deep learning-based techniques. The proposed model achieves 95% accuracy, 97% recall, having a precision of 95% with an F1-score of 96% demonstrating its effectiveness in sentiment analysis of student feedback.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"8 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Indirect aggression has become a prevalent phenomenon that erodes the social media environment. Due to the expense and the difficulty in determining objectively what constitutes indirect aggression, the traditional self-reporting questionnaire is hard to be employed in the current cyber area. In this study, we present a model for predicting indirect aggression online based on pre-trained models. Building on Weibo users’ social media activities, we constructed basic, dynamic, and content features and classified indirect aggression into three subtypes: social exclusion, malicious humour, and guilt induction. We then built the prediction model by combining it with large-scale pre-trained models. The empirical evidence shows that this prediction model (ERNIE) outperforms the pre-trained models and predicts indirect aggression online much better than the models without extra pre-trained information. This study offers a practical model to predict users’ indirect aggression. Furthermore, this work contributes to a better understanding of indirect aggression behaviors and can support social media platforms’ organization and management.
{"title":"Predicting social media users’ indirect aggression through pre-trained models","authors":"Zhenkun Zhou, Mengli Yu, Xingyu Peng, Yuxin He","doi":"10.7717/peerj-cs.2292","DOIUrl":"https://doi.org/10.7717/peerj-cs.2292","url":null,"abstract":"Indirect aggression has become a prevalent phenomenon that erodes the social media environment. Due to the expense and the difficulty in determining objectively what constitutes indirect aggression, the traditional self-reporting questionnaire is hard to be employed in the current cyber area. In this study, we present a model for predicting indirect aggression online based on pre-trained models. Building on Weibo users’ social media activities, we constructed basic, dynamic, and content features and classified indirect aggression into three subtypes: social exclusion, malicious humour, and guilt induction. We then built the prediction model by combining it with large-scale pre-trained models. The empirical evidence shows that this prediction model (ERNIE) outperforms the pre-trained models and predicts indirect aggression online much better than the models without extra pre-trained information. This study offers a practical model to predict users’ indirect aggression. Furthermore, this work contributes to a better understanding of indirect aggression behaviors and can support social media platforms’ organization and management.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"168 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cem Kaya, Zeynep Hilal Kilimci, Mitat Uysal, Murat Kaya
Text classification tasks, particularly those involving a large number of features, pose significant challenges in effective feature selection. This research introduces a novel methodology, MBO-NB, which integrates Migrating Birds Optimization (MBO) approach with naïve Bayes as an internal classifier to address these challenges. The motivation behind this study stems from the recognized limitations of existing techniques in efficiently handling extensive feature sets. Traditional approaches often fail to adequately streamline the feature selection process, resulting in suboptimal classification accuracy and increased computational overhead. In response to this need, our primary objective is to propose a scalable and effective solution that enhances both computational efficiency and classification accuracy in text classification systems. To achieve this objective, we preprocess raw data using the Information Gain algorithm, strategically reducing the feature count from an average of 62,221 to 2,089. Through extensive experiments, we demonstrate the superior effectiveness of MBO-NB in feature reduction compared to other existing techniques, resulting in significantly improved classification accuracy. Furthermore, the successful integration of naïve Bayes within MBO offers a comprehensive and well-rounded solution to the feature selection problem. In individual comparisons with Particle Swarm Optimization (PSO), MBO-NB consistently outperforms by an average of 6.9% across four setups. This research provides valuable insights into enhancing feature selection methods, thereby contributing to the advancement of text classification techniques. By offering a scalable and effective solution, MBO-NB addresses the pressing need for improved feature selection methods in text classification, thereby facilitating the development of more robust and efficient classification systems.
{"title":"Migrating birds optimization-based feature selection for text classification","authors":"Cem Kaya, Zeynep Hilal Kilimci, Mitat Uysal, Murat Kaya","doi":"10.7717/peerj-cs.2263","DOIUrl":"https://doi.org/10.7717/peerj-cs.2263","url":null,"abstract":"Text classification tasks, particularly those involving a large number of features, pose significant challenges in effective feature selection. This research introduces a novel methodology, MBO-NB, which integrates Migrating Birds Optimization (MBO) approach with naïve Bayes as an internal classifier to address these challenges. The motivation behind this study stems from the recognized limitations of existing techniques in efficiently handling extensive feature sets. Traditional approaches often fail to adequately streamline the feature selection process, resulting in suboptimal classification accuracy and increased computational overhead. In response to this need, our primary objective is to propose a scalable and effective solution that enhances both computational efficiency and classification accuracy in text classification systems. To achieve this objective, we preprocess raw data using the Information Gain algorithm, strategically reducing the feature count from an average of 62,221 to 2,089. Through extensive experiments, we demonstrate the superior effectiveness of MBO-NB in feature reduction compared to other existing techniques, resulting in significantly improved classification accuracy. Furthermore, the successful integration of naïve Bayes within MBO offers a comprehensive and well-rounded solution to the feature selection problem. In individual comparisons with Particle Swarm Optimization (PSO), MBO-NB consistently outperforms by an average of 6.9% across four setups. This research provides valuable insights into enhancing feature selection methods, thereby contributing to the advancement of text classification techniques. By offering a scalable and effective solution, MBO-NB addresses the pressing need for improved feature selection methods in text classification, thereby facilitating the development of more robust and efficient classification systems.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"124 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study aims to address a variant of the hybrid flow shop problem by simultaneously integrating lag times, unloading times, and transportation times, with the goal of minimizing the maximum completion time, or makespan. With applications in image processing, manufacturing, and industrial environments, this problem presents significant theoretical challenges, being classified as NP-hard. Notably, the problem demonstrates a notable symmetry property, resulting in a symmetric problem formulation where both the scheduling problem and its symmetric counterpart share the same optimal solution. To improve solution quality, all proposed procedures are extended to the symmetric problem. This research pioneers the consideration of the hybrid flow shop scheduling problem with simultaneous attention to lag, unloading, and transportation times, building upon a comprehensive review of existing literature. A two-phase heuristic is introduced as a solution to this complex problem, involving iterative solving of parallel machine scheduling problems. This approach decomposes the problem into manageable sub-problems, facilitating focused and efficient resolution. The efficient solving of sub-problems using the developed heuristic yields satisfactory near-optimal solutions. Additionally, two new lower bounds are proposed, derived from estimating minimum idle time within each stage via solving a polynomial parallel machine problem aimed at minimizing total flow time. These lower bounds serve to evaluate the performance of the developed two-phase heuristic, over measuring the relative gap. Extensive experimental studies on benchmark test problems of varying sizes demonstrate the effectiveness of the proposed approaches. All test problems are efficiently solved within reasonable timeframes, indicating practicality and efficiency. The proposed methods exhibit an average computational time of 8.93 seconds and an average gap of 2.75%. These computational results underscore the efficacy and potential applicability of the proposed approaches in real-world scenarios, providing valuable insights and paving the way for further research and practical implementations in hybrid flow shop scheduling.
{"title":"Multi-stage hybrid flow shop scheduling problem with lag, unloading, and transportation times","authors":"Lotfi Hidri, Mehdi Tlija","doi":"10.7717/peerj-cs.2168","DOIUrl":"https://doi.org/10.7717/peerj-cs.2168","url":null,"abstract":"This study aims to address a variant of the hybrid flow shop problem by simultaneously integrating lag times, unloading times, and transportation times, with the goal of minimizing the maximum completion time, or makespan. With applications in image processing, manufacturing, and industrial environments, this problem presents significant theoretical challenges, being classified as NP-hard. Notably, the problem demonstrates a notable symmetry property, resulting in a symmetric problem formulation where both the scheduling problem and its symmetric counterpart share the same optimal solution. To improve solution quality, all proposed procedures are extended to the symmetric problem. This research pioneers the consideration of the hybrid flow shop scheduling problem with simultaneous attention to lag, unloading, and transportation times, building upon a comprehensive review of existing literature. A two-phase heuristic is introduced as a solution to this complex problem, involving iterative solving of parallel machine scheduling problems. This approach decomposes the problem into manageable sub-problems, facilitating focused and efficient resolution. The efficient solving of sub-problems using the developed heuristic yields satisfactory near-optimal solutions. Additionally, two new lower bounds are proposed, derived from estimating minimum idle time within each stage via solving a polynomial parallel machine problem aimed at minimizing total flow time. These lower bounds serve to evaluate the performance of the developed two-phase heuristic, over measuring the relative gap. Extensive experimental studies on benchmark test problems of varying sizes demonstrate the effectiveness of the proposed approaches. All test problems are efficiently solved within reasonable timeframes, indicating practicality and efficiency. The proposed methods exhibit an average computational time of 8.93 seconds and an average gap of 2.75%. These computational results underscore the efficacy and potential applicability of the proposed approaches in real-world scenarios, providing valuable insights and paving the way for further research and practical implementations in hybrid flow shop scheduling.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"2 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scene-based image semantic extraction and its precise sentiment expression significantly enhance artistic design. To address the incongruity between image features and sentiment features caused by non-bilinear pooling, this study introduces a generative adversarial network (GAN) model that integrates visual relationships with sentiment semantics. The GAN-based regularizer is utilized during training to incorporate target information derived from the contextual information into the process. This regularization mechanism imposes stronger penalties for inaccuracies in subject-object type predictions and integrates a sentiment corpus to generate more human-like descriptive statements. The capsule network is employed to reconstruct sentences and predict probabilities in the discriminator. To preserve crucial focal points in feature extraction, the Convolutional Block Attention Mechanism (CBAM) is introduced. Furthermore, two bidirectional long short-term memory (LSTM) modules are used to model both target and relational contexts, thereby refining target labels and inter-target relationships. Experimental results highlight the model’s superiority over comparative models in terms of accuracy, BiLingual Evaluation Understudy (BLEU) score, and text preservation rate. The proposed model achieves an accuracy of 95.40% and the highest BLEU score of 16.79, effectively capturing both the label content and the emotional nuances within the image.
基于场景的图像语义提取及其精确的情感表达能显著提升艺术设计的效果。为了解决非线性汇集造成的图像特征与情感特征之间的不协调问题，本研究引入了一种生成对抗网络（GAN）模型，将视觉关系与情感语义整合在一起。在训练过程中利用基于 GAN 的正则化机制，将从上下文信息中获得的目标信息纳入训练过程。这种正则化机制会对主客体类型预测的不准确性施加更强的惩罚，并整合情感语料库以生成更像人的描述性语句。胶囊网络用于重构句子和预测判别器中的概率。为了在特征提取中保留关键焦点，引入了卷积块注意机制（CBAM）。此外，两个双向长短期记忆（LSTM）模块用于对目标和关系上下文进行建模，从而完善目标标签和目标间关系。实验结果表明，该模型在准确率、双语评估得分（BLEU）和文本保留率方面均优于同类模型。所提模型的准确率达到 95.40%，BLEU 得分最高，为 16.79 分，有效捕捉了图像中的标签内容和情感细微差别。
{"title":"Art design integrating visual relation and affective semantics based on Convolutional Block Attention Mechanism-generative adversarial network model","authors":"Jiadong Shen, Jian Wang","doi":"10.7717/peerj-cs.2274","DOIUrl":"https://doi.org/10.7717/peerj-cs.2274","url":null,"abstract":"Scene-based image semantic extraction and its precise sentiment expression significantly enhance artistic design. To address the incongruity between image features and sentiment features caused by non-bilinear pooling, this study introduces a generative adversarial network (GAN) model that integrates visual relationships with sentiment semantics. The GAN-based regularizer is utilized during training to incorporate target information derived from the contextual information into the process. This regularization mechanism imposes stronger penalties for inaccuracies in subject-object type predictions and integrates a sentiment corpus to generate more human-like descriptive statements. The capsule network is employed to reconstruct sentences and predict probabilities in the discriminator. To preserve crucial focal points in feature extraction, the Convolutional Block Attention Mechanism (CBAM) is introduced. Furthermore, two bidirectional long short-term memory (LSTM) modules are used to model both target and relational contexts, thereby refining target labels and inter-target relationships. Experimental results highlight the model’s superiority over comparative models in terms of accuracy, BiLingual Evaluation Understudy (BLEU) score, and text preservation rate. The proposed model achieves an accuracy of 95.40% and the highest BLEU score of 16.79, effectively capturing both the label content and the emotional nuances within the image.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"9 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shengjie Xia, Wu Sun, Xiaofeng Zou, Panfeng Chen, Dan Ma, Huarong Xu, Mei Chen, Hui Li
Multivariate time series anomaly detection has garnered significant attention in fields such as IT operations, finance, medicine, and industry. However, a key challenge lies in the fact that anomaly patterns often exhibit multi-scale temporal variations, which existing detection models often fail to capture effectively. This limitation significantly impacts detection accuracy. To address this issue, we propose the MFAM-AD model, which combines the strengths of convolutional neural networks (CNNs) and bi-directional long short-term memory (Bi-LSTM). The MFAM-AD model is designed to enhance anomaly detection accuracy by seamlessly integrating temporal dependencies and multi-scale spatial features. Specifically, it utilizes parallel convolutional layers to extract features across different scales, employing an attention mechanism for optimal feature fusion. Additionally, Bi-LSTM is leveraged to capture time-dependent information, reconstruct the time series and enable accurate anomaly detection based on reconstruction errors. In contrast to existing algorithms that struggle with inadequate feature fusion or are confined to single-scale feature analysis, MFAM-AD effectively addresses the unique challenges of multivariate time series anomaly detection. Experimental results on five publicly available datasets demonstrate the superiority of the proposed model. Specifically, on the datasets SMAP, MSL, and SMD1-1, our MFAM-AD model has the second-highest F1 score after the current state-of-the-art DCdetector model. On the datasets NIPS-TS-SWAN and NIPS-TS-GECCO, the F1 scores of MAFM-AD are 0.046 (6.2%) and 0.09 (21.3%) higher than those of DCdetector, respectively(the value ranges from 0 to 1). These findings validate the MFAMAD model’s efficacy in multivariate time series anomaly detection, highlighting its potential in various real-world applications.
{"title":"MFAM-AD: an anomaly detection model for multivariate time series using attention mechanism to fuse multi-scale features","authors":"Shengjie Xia, Wu Sun, Xiaofeng Zou, Panfeng Chen, Dan Ma, Huarong Xu, Mei Chen, Hui Li","doi":"10.7717/peerj-cs.2201","DOIUrl":"https://doi.org/10.7717/peerj-cs.2201","url":null,"abstract":"Multivariate time series anomaly detection has garnered significant attention in fields such as IT operations, finance, medicine, and industry. However, a key challenge lies in the fact that anomaly patterns often exhibit multi-scale temporal variations, which existing detection models often fail to capture effectively. This limitation significantly impacts detection accuracy. To address this issue, we propose the MFAM-AD model, which combines the strengths of convolutional neural networks (CNNs) and bi-directional long short-term memory (Bi-LSTM). The MFAM-AD model is designed to enhance anomaly detection accuracy by seamlessly integrating temporal dependencies and multi-scale spatial features. Specifically, it utilizes parallel convolutional layers to extract features across different scales, employing an attention mechanism for optimal feature fusion. Additionally, Bi-LSTM is leveraged to capture time-dependent information, reconstruct the time series and enable accurate anomaly detection based on reconstruction errors. In contrast to existing algorithms that struggle with inadequate feature fusion or are confined to single-scale feature analysis, MFAM-AD effectively addresses the unique challenges of multivariate time series anomaly detection. Experimental results on five publicly available datasets demonstrate the superiority of the proposed model. Specifically, on the datasets SMAP, MSL, and SMD1-1, our MFAM-AD model has the second-highest F1 score after the current state-of-the-art DCdetector model. On the datasets NIPS-TS-SWAN and NIPS-TS-GECCO, the F1 scores of MAFM-AD are 0.046 (6.2%) and 0.09 (21.3%) higher than those of DCdetector, respectively(the value ranges from 0 to 1). These findings validate the MFAMAD model’s efficacy in multivariate time series anomaly detection, highlighting its potential in various real-world applications.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"6 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Imran Ullah, Khalil Ullah, Hamad Khan, Khursheed Aurangzeb, Muhammad Shahid Anwar, Ikram Syed
Generating poetry using machine and deep learning techniques has been a challenging and exciting topic of research in recent years. It has significance in natural language processing and computational linguistics. This study introduces an innovative approach to generate high-quality Pashto poetry by leveraging two pre-trained transformer models, LaMini-Cerebras-590M and bloomz-560m. The models were trained on an extensive new and quality Pashto poetry dataset to learn the underlying complex patterns and structures. The trained models are then used to generate new Pashto poetry by providing them with a seed text or prompt. To evaluate the quality of the generated poetry, we conducted both subjective and objective evaluations, including human evaluation. The experimental results demonstrate that the proposed approach can generate Pashto poetry that is comparable in quality to human-generated poetry. The study provides a valuable contribution to the field of Pashto language and poetry generation and has potential applications in natural language processing and computational linguistics.
{"title":"Pashto poetry generation: deep learning with pre-trained transformers for low-resource languages","authors":"Imran Ullah, Khalil Ullah, Hamad Khan, Khursheed Aurangzeb, Muhammad Shahid Anwar, Ikram Syed","doi":"10.7717/peerj-cs.2163","DOIUrl":"https://doi.org/10.7717/peerj-cs.2163","url":null,"abstract":"Generating poetry using machine and deep learning techniques has been a challenging and exciting topic of research in recent years. It has significance in natural language processing and computational linguistics. This study introduces an innovative approach to generate high-quality Pashto poetry by leveraging two pre-trained transformer models, LaMini-Cerebras-590M and bloomz-560m. The models were trained on an extensive new and quality Pashto poetry dataset to learn the underlying complex patterns and structures. The trained models are then used to generate new Pashto poetry by providing them with a seed text or prompt. To evaluate the quality of the generated poetry, we conducted both subjective and objective evaluations, including human evaluation. The experimental results demonstrate that the proposed approach can generate Pashto poetry that is comparable in quality to human-generated poetry. The study provides a valuable contribution to the field of Pashto language and poetry generation and has potential applications in natural language processing and computational linguistics.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"16 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142203477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：