Neural Computing & Applications最新文献

{"title":"A systematic review of machine learning techniques for stance detection and its applications.","authors":"Nora Alturayeif, Hamzah Luqman, Moataz Ahmed","doi":"10.1007/s00521-023-08285-7","DOIUrl":"10.1007/s00521-023-08285-7","url":null,"abstract":"<p><p>Stance detection is an evolving opinion mining research area motivated by the vast increase in the variety and volume of user-generated content. In this regard, considerable research has been recently carried out in the area of stance detection. In this study, we review the different techniques proposed in the literature for stance detection as well as other applications such as rumor veracity detection. Particularly, we conducted a systematic literature review of empirical research on the machine learning (ML) models for stance detection that were published from January 2015 to October 2022. We analyzed 96 primary studies, which spanned eight categories of ML techniques. In this paper, we categorize the analyzed studies according to a taxonomy of six dimensions: approaches, target dependency, applications, modeling, language, and resources. We further classify and analyze the corresponding techniques from each dimension's perspective and highlight their strengths and weaknesses. The analysis reveals that deep learning models that adopt a mechanism of self-attention have been used more frequently than the other approaches. It is worth noting that emerging ML techniques such as few-shot learning and multitask learning have been used extensively for stance detection. A major conclusion of our analysis is that despite that ML models have shown to be promising in this field, the application of these models in the real world is still limited. Our analysis lists challenges and gaps to be addressed in future research. Furthermore, the taxonomy presented can assist researchers in developing and positioning new techniques for stance detection-related applications.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 7","pages":"5113-5144"},"PeriodicalIF":4.5,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9884072/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10642878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"CovTiNet: Covid text identification network using attention-based positional embedding feature fusion.","authors":"Md Rajib Hossain,&nbsp;Mohammed Moshiul Hoque,&nbsp;Nazmul Siddique,&nbsp;Iqbal H Sarker","doi":"10.1007/s00521-023-08442-y","DOIUrl":"https://doi.org/10.1007/s00521-023-08442-y","url":null,"abstract":"<p><p>Covid text identification (CTI) is a crucial research concern in natural language processing (NLP). Social and electronic media are simultaneously adding a large volume of Covid-affiliated text on the World Wide Web due to the effortless access to the Internet, electronic gadgets and the Covid outbreak. Most of these texts are uninformative and contain misinformation, disinformation and malinformation that create an infodemic. Thus, Covid text identification is essential for controlling societal distrust and panic. Though very little Covid-related research (such as Covid disinformation, misinformation and fake news) has been reported in high-resource languages (e.g. English), CTI in low-resource languages (like Bengali) is in the preliminary stage to date. However, automatic CTI in Bengali text is challenging due to the deficit of benchmark corpora, complex linguistic constructs, immense verb inflexions and scarcity of NLP tools. On the other hand, the manual processing of Bengali Covid texts is arduous and costly due to their messy or unstructured forms. This research proposes a deep learning-based network (CovTiNet) to identify Covid text in Bengali. The CovTiNet incorporates an attention-based position embedding feature fusion for text-to-feature representation and attention-based CNN for Covid text identification. Experimental results show that the proposed CovTiNet achieved the highest accuracy of 96.61±.001% on the developed dataset (<i>BCovC</i>) compared to the other methods and baselines (i.e. BERT-M, IndicBERT, ELECTRA-Bengali, DistilBERT-M, BiLSTM, DCNN, CNN, LSTM, VDCNN and ACNN).</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 18","pages":"13503-13527"},"PeriodicalIF":6.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10011801/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9507549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"An optimized model for network intrusion detection systems in industry 4.0 using XAI based Bi-LSTM framework.","authors":"S Sivamohan,&nbsp;S S Sridhar","doi":"10.1007/s00521-023-08319-0","DOIUrl":"https://doi.org/10.1007/s00521-023-08319-0","url":null,"abstract":"<p><p>Industry 4.0 enable novel business cases, such as client-specific production, real-time monitoring of process condition and progress, independent decision making and remote maintenance, to name a few. However, they are more susceptible to a broad range of cyber threats because of limited resources and heterogeneous nature. Such risks cause financial and reputational damages for businesses, well as the theft of sensitive information. The higher level of diversity in industrial network prevents the attackers from such attacks. Therefore, to efficiently detect the intrusions, a novel intrusion detection system known as Bidirectional Long Short-Term Memory based Explainable Artificial Intelligence framework (BiLSTM-XAI) is developed. Initially, the preprocessing task using data cleaning and normalization is performed to enhance the data quality for detecting network intrusions. Subsequently, the significant features are selected from the databases using the Krill herd optimization (KHO) algorithm. The proposed BiLSTM-XAI approach provides better security and privacy inside the industry networking system by detecting intrusions very precisely. In this, we utilized SHAP and LIME explainable AI algorithms to improve interpretation of prediction results. The experimental setup is made by MATLAB 2016 software using Honeypot and NSL-KDD datasets as input. The analysis result reveals that the proposed method achieves superior performance in detecting intrusions with a classification accuracy of 98.2%.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 15","pages":"11459-11475"},"PeriodicalIF":6.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9999327/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9439695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Development and external evaluation of predictions models for mortality of COVID-19 patients using machine learning method.","authors":"Simin Li,&nbsp;Yulan Lin,&nbsp;Tong Zhu,&nbsp;Mengjie Fan,&nbsp;Shicheng Xu,&nbsp;Weihao Qiu,&nbsp;Can Chen,&nbsp;Linfeng Li,&nbsp;Yao Wang,&nbsp;Jun Yan,&nbsp;Justin Wong,&nbsp;Lin Naing,&nbsp;Shabei Xu","doi":"10.1007/s00521-020-05592-1","DOIUrl":"https://doi.org/10.1007/s00521-020-05592-1","url":null,"abstract":"<p><p>To predict the mortality of patients with coronavirus disease 2019 (COVID-19). We collected clinical data of COVID-19 patients between January 18 and March 29 2020 in Wuhan, China . Gradient boosting decision tree (GBDT), logistic regression (LR) model, and simplified LR were built to predict the mortality of COVID-19. We also evaluated different models by computing area under curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV) under fivefold cross-validation. A total of 2924 patients were included in our evaluation, with 257 (8.8%) died and 2667 (91.2%) survived during hospitalization. Upon admission, there were 21 (0.7%) mild cases, 2051 (70.1%) moderate case, 779 (26.6%) severe cases, and 73 (2.5%) critically severe cases. The GBDT model exhibited the highest fivefold AUC, which was 0.941, followed by LR (0.928) and LR-5 (0.913). The diagnostic accuracies of GBDT, LR, and LR-5 were 0.889, 0.868, and 0.887, respectively. In particular, the GBDT model demonstrated the highest sensitivity (0.899) and specificity (0.889). The NPV of all three models exceeded 97%, while their PPV values were relatively low, resulting in 0.381 for LR, 0.402 for LR-5, and 0.432 for GBDT. Regarding severe and critically severe cases, the GBDT model also performed the best with a fivefold AUC of 0.918. In the external validation test of the LR-5 model using 72 cases of COVID-19 from Brunei, leukomonocyte (%) turned to show the highest fivefold AUC (0.917), followed by urea (0.867), age (0.826), and SPO2 (0.704). The findings confirm that the mortality prediction performance of the GBDT is better than the LR models in confirmed cases of COVID-19. The performance comparison seems independent of disease severity.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at(10.1007/s00521-020-05592-1).</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 18","pages":"13037-13046"},"PeriodicalIF":6.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/s00521-020-05592-1","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9853876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"ABOA-CNN: auction-based optimization algorithm with convolutional neural network for pulmonary disease prediction.","authors":"Balaji Annamalai,&nbsp;Prabakeran Saravanan,&nbsp;Indumathi Varadharajan","doi":"10.1007/s00521-022-08033-3","DOIUrl":"https://doi.org/10.1007/s00521-022-08033-3","url":null,"abstract":"<p><p>Nowadays, deep learning plays a vital role behind many of the emerging technologies. Few applications of deep learning include speech recognition, virtual assistant, healthcare, entertainment, and so on. In healthcare applications, deep learning can be used to predict diseases effectively. It is a type of computer model that learns in conducting classification tasks directly from text, sound, or images. It also provides better accuracy and sometimes outdoes human performance. We presented a novel approach that makes use of the deep learning method in our proposed work. The prediction of pulmonary disease can be performed with the aid of convolutional neural network (CNN) incorporated with auction-based optimization algorithm (ABOA) and DSC process. The traditional CNN ignores the dominant features from the X-ray images while performing the feature extraction process. This can be effectively circumvented by the adoption of ABOA, and the DSC is used to classify the pulmonary disease types such as fibrosis, pneumonia, cardiomegaly, and normal from the X-ray images. We have taken two datasets, namely the NIH Chest X-ray dataset and ChestX-ray8. The performances of the proposed approach are compared with deep learning-based state-of-art works such as BPD, DL, CSS-DL, and Grad-CAM. From the performance analyses, it is confirmed that the proposed approach effectively extracts the features from the X-ray images, and thus, the prediction of pulmonary diseases is more accurate than the state-of-art approaches.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 10","pages":"7463-7474"},"PeriodicalIF":6.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9910772/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9506281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 new YOLO-based method for social distancing from real-time videos.","authors":"Mehmet Şirin Gündüz,&nbsp;Gültekin Işık","doi":"10.1007/s00521-023-08556-3","DOIUrl":"10.1007/s00521-023-08556-3","url":null,"abstract":"<p><p>The coronavirus disease (COVID-19) is primarily disseminated through physical contact. As a precaution, it is recommended that indoor spaces have a limited number of people and at least one meter apart. This study proposes a real-time method for monitoring physical distancing compliance in indoor spaces using computer vision and deep learning techniques. The proposed method utilizes YOLO (You Only Look Once), a popular convolutional neural network-based object detection model, pre-trained on the Microsoft COCO (Common Objects in Context) dataset to detect persons and estimate their physical distance in real time. The effectiveness of the proposed method was assessed using metrics including accuracy rate, frame per second (FPS), and mean average precision (mAP). The results show that the YOLO v3 model had the most remarkable accuracy (87.07%) and mAP (89.91%). On the other hand, the highest fps rate of up to 18.71 was achieved by the YOLO v5s model. The results demonstrate the potential of the proposed method for effectively monitoring physical distancing compliance in indoor spaces, providing valuable insights for future use in other public health scenarios.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 21","pages":"15261-15271"},"PeriodicalIF":6.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10081816/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9576902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Automated semantic lung segmentation in chest CT images using deep neural network.","authors":"M Murugappan, Ali K Bourisly, N B Prakash, M G Sumithra, U Rajendra Acharya","doi":"10.1007/s00521-023-08407-1","DOIUrl":"10.1007/s00521-023-08407-1","url":null,"abstract":"<p><p>Lung segmentation algorithms play a significant role in segmenting theinfected regions in the lungs. This work aims to develop a computationally efficient and robust deep learning model for lung segmentation using chest computed tomography (CT) images with DeepLabV3 + networks for two-class (background and lung field) and four-class (ground-glass opacities, background, consolidation, and lung field). In this work, we investigate the performance of the DeepLabV3 + network with five pretrained networks: Xception, ResNet-18, Inception-ResNet-v2, MobileNet-v2 and ResNet-50. A publicly available database for COVID-19 that contains 750 chest CT images and corresponding pixel-labeled images are used to develop the deep learning model. The segmentation performance has been assessed using five performance measures: Intersection of Union (IoU), Weighted IoU, Balance F1 score, pixel accu-racy, and global accuracy. The experimental results of this work confirm that the DeepLabV3 + network with ResNet-18 and a batch size of 8 have a higher performance for two-class segmentation. DeepLabV3 + network coupled with ResNet-50 and a batch size of 16 yielded better results for four-class segmentation compared to other pretrained networks. Besides, the ResNet with a fewer number of layers is highly adequate for developing a more robust lung segmentation network with lesser computational complexity compared to the conventional DeepLabV3 + network with Xception. This present work proposes a unified DeepLabV3 + network to delineate the two and four different regions automatically using CT images for CoVID-19 patients. Our developed automated segmented model can be further developed to be used as a clinical diagnosis system for CoVID-19 as well as assist clinicians in providing an accurate second opinion CoVID-19 diagnosis.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 21","pages":"15343-15364"},"PeriodicalIF":4.5,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10088735/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9570242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Boosting Archimedes optimization algorithm using trigonometric operators based on feature selection for facial analysis.","authors":"Imène Neggaz,&nbsp;Nabil Neggaz,&nbsp;Hadria Fizazi","doi":"10.1007/s00521-022-07925-8","DOIUrl":"https://doi.org/10.1007/s00521-022-07925-8","url":null,"abstract":"<p><p>Due to technical advancements and the proliferation of mobile applications, facial analysis (FA) of humans has recently become an important area for computer vision research. FA investigates a variety of difficulties, including gender recognition, facial expression recognition, age and race recognition, with the goal of automatically comprehending social interactions. Due to the dimensional challenge posed by pre-trained CNN networks, the scientific community has developed numerous techniques inspired by biology, swarm intelligence theory, physics, and mathematical rules. This article presents a gender recognition system based on scAOA, that is a modified version of the Archimedes optimization algorithm (AOA). The latest variant (scAOA) enhances the exploitation stage by using trigonometric operators inspired by the sine cosine algorithm (SCA) in order to prevent local optima and to accelerate the convergence. The main purpose of this paper is to apply scAOA to select the relevant deep features provided by two pretrained models of CNN (AlexNet & ResNet) to recognize the gender of a human person categorized into two classes (men and women). Two datasets are used to evaluate the proposed approach (scAOA): the Brazilian FEI dataset and the Georgia Tech Face dataset (GT). In terms of accuracy, Fscore and statistical test, the comparison analysis demonstrates that scAOA outperforms other modern and competitive optimizers such as AOA, SCA, Ant lion optimizer (ALO), Salp swarm algorithm (SSA), Grey wolf optimizer (GWO), Simple genetic algorithm (SGA), Grasshopper optimization algorithm (GOA) and Particle swarm optimizer (PSO).</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 5","pages":"3903-3923"},"PeriodicalIF":6.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9569187/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10622872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 cyber warfare perspective on risks related to health IoT devices and contact tracing.","authors":"Andrea Bobbio,&nbsp;Lelio Campanile,&nbsp;Marco Gribaudo,&nbsp;Mauro Iacono,&nbsp;Fiammetta Marulli,&nbsp;Michele Mastroianni","doi":"10.1007/s00521-021-06720-1","DOIUrl":"10.1007/s00521-021-06720-1","url":null,"abstract":"<p><p>The wide use of IT resources to assess and manage the recent COVID-19 pandemic allows to increase the effectiveness of the countermeasures and the pervasiveness of monitoring and prevention. Unfortunately, the literature reports that IoT devices, a widely adopted technology for these applications, are characterized by security vulnerabilities that are difficult to manage at the state level. Comparable problems exist for related technologies that leverage smartphones, such as contact tracing applications, and non-medical health monitoring devices. In analogous situations, these vulnerabilities may be exploited in the cyber domain to overload the crisis management systems with false alarms and to interfere with the interests of target countries, with consequences on their economy and their political equilibria. In this paper we analyze the potential threat to an example subsystem to show how these influences may impact it and evaluate a possible consequence.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 19","pages":"13823-13837"},"PeriodicalIF":6.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8769794/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9524521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Identification and classification of pneumonia disease using a deep learning-based intelligent computational framework.","authors":"Rong Yi,&nbsp;Lanying Tang,&nbsp;Yuqiu Tian,&nbsp;Jie Liu,&nbsp;Zhihui Wu","doi":"10.1007/s00521-021-06102-7","DOIUrl":"10.1007/s00521-021-06102-7","url":null,"abstract":"<p><p>Pneumonia is one of the hazardous diseases that lead to life insecurity. It needs to be diagnosed at the initial stages to prevent a person from more damage and help them save their lives. Various techniques are used to identify pneumonia, including chest X-ray, blood culture, sputum culture, fluid sample, bronchoscopy, and pulse oximetry. Chest X-ray is the most widely used method to diagnose pneumonia and is considered one of the most reliable approaches. To analyse chest X-ray images accurately, an expert radiologist needs expertise and experience in the desired domain. However, human-assisted approaches have some drawbacks: expert availability, treatment cost, availability of diagnostic tools, etc. Hence, the need for an intelligent and automated system comes into place that operates on chest X-ray images and diagnoses pneumonia. The primary purpose of technology is to develop algorithms and tools that assist humans and make their lives easier. This study proposes a scalable and interpretable deep convolutional neural network (DCNN) to identify pneumonia using chest X-ray images. The proposed modified DCNN model first extracts useful features from the images and then classifies them into normal and pneumonia classes. The proposed system has been trained and tested on chest X-ray images dataset. Various performance metrics have been utilized to inspect the stability and efficacy of the proposed model. The experimental result shows that the proposed model's performance is greater compared to the other state-of-the-art methodologies used to identify pneumonia.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"35 20","pages":"14473-14486"},"PeriodicalIF":6.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/s00521-021-06102-7","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9565919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}