Expert Systems最新文献_第8页

Flexible Distribution Approaches to Enhance Regression and Deep Topic Modelling Techniques

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-25 DOI: 10.1111/exsy.13789

Pantea Koochemeshkian, Nizar Bouguila

{"title":"Flexible Distribution Approaches to Enhance Regression and Deep Topic Modelling Techniques","authors":"Pantea Koochemeshkian, Nizar Bouguila","doi":"10.1111/exsy.13789","DOIUrl":"https://doi.org/10.1111/exsy.13789","url":null,"abstract":"<p>This paper presents an extension of the Dirichlet multinomial regression (DMR) and deep Dirichlet multinomial regression (dDMR) topic modelling approaches by incorporating the generalised Dirichlet (GD) and Beta-Liouville (BL) distributions using collapsed Gibbs sampling for parameter inference. The DMR and dDMR approaches have been shown to be effective in discovering latent topics in text corpora. However, these approaches have limitations when it comes to handling complex data structures and overfitting issues. To address these limitations, we introduce the GD and BL distributions, which have more flexibility in modelling complex data structures and handling sparse data. Additionally, we use collapsed Gibbs sampling to estimate the model parameters, which provides a computationally efficient method for inference. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed approach in improving topic modelling performance, particularly in handling complex data structures and reducing overfitting. The proposed models also exhibit good interpretability of the learned topics, making them suitable for various applications in natural language processing and machine learning.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.13789","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143119040","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}

引用次数: 0

An Ontology for In-Depth Description of User Situations in Connected Environments

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-25 DOI: 10.1111/exsy.13792

Karam Bou-Chaaya, Richard Chbeir, Mahmoud Barhamgi, Philippe Arnould, Benslimane Djamal

{"title":"An Ontology for In-Depth Description of User Situations in Connected Environments","authors":"Karam Bou-Chaaya, Richard Chbeir, Mahmoud Barhamgi, Philippe Arnould, Benslimane Djamal","doi":"10.1111/exsy.13792","DOIUrl":"https://doi.org/10.1111/exsy.13792","url":null,"abstract":"<div>\u0000 \u0000 <p>Context-awareness is increasingly recognised as a fundamental principle in the development of ubiquitous computing and ambient intelligence. By leveraging contextual data about users and their environments, systems can gain a deeper understanding of the evolving user situation. This empowers them to dynamically adapt their operations, leading to optimised resource utilisation, enhanced decision-making, and ultimately, greater user satisfaction. However, a critical challenge lies in effectively representing user situations with a high degree of expressiveness. While ontology-based data models have emerged as a promising approach due to their ability to handle the inherent heterogeneity of context information, existing ontologies have limitations in terms of information coverage, data heterogeneity and uncertainties consideration, and reusability across various application domains. This paper addresses these limitations by proposing uCSN, an ontology that builds upon and extends the Data Privacy Vocabulary (DPV), Semantic Sensor Network (SSN) and W3C Uncertainty ontologies, to provide a rich and expressive vocabulary for representing diverse user situations. We evaluate uCSN based on its consistency, accuracy, clarity and performance.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143119041","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}

引用次数: 0

Fog Computing for Artificial Intelligence Digital Textbooks: Educational Scaffolding and Security and Privacy Challenges

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-23 DOI: 10.1111/exsy.13801

Pyoung Won Kim

{"title":"Fog Computing for Artificial Intelligence Digital Textbooks: Educational Scaffolding and Security and Privacy Challenges","authors":"Pyoung Won Kim","doi":"10.1111/exsy.13801","DOIUrl":"https://doi.org/10.1111/exsy.13801","url":null,"abstract":"<div>\u0000 \u0000 <p>Digital textbooks (DTs) have evolved from DT 1.0, which simply converted paper textbooks to PDF format, to DT 2.0, which provides various multimedia content, for example, video and audio content. DTs have now advanced to DT 3.0, which enhances learner engagement through gamification and simulations. Recently, with the advancement of cloud computing technology and digital devices, for example, tablets, DT 4.0, which supports personalised learning through artificial intelligence (AI) tutors and chatbots, has been realised. South Korea is actively implementing a policy to distribute artificial intelligence–based DTs, equivalent to DT 4.0, to all schools under national leadership. For artificial intelligence–based DTs (AIDTs) in South Korea to develop into a sustainable education system, reliance on cloud computing alone is insufficient. It is also necessary to build layers of fog computing and edge computing from the initial stage. There are concerns that AIDTs may exacerbate the learning gap because they are more likely to be utilised actively by high-performing students with established self-directed learning habits rather than struggling students. Thus, it is essential to enhance usage monitoring and explore strategies that provide educational scaffolding to prevent differences in the level of AIDT utilisation from leading to a widening learning gap.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143118662","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}

引用次数: 0

Intrusion Detection Using CTGAN and Lightweight Neural Network for Internet of Things

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-21 DOI: 10.1111/exsy.13793

Sudeshna Das, Abhishek Majumder, Suyel Namasudra, Ashish Singh

{"title":"Intrusion Detection Using CTGAN and Lightweight Neural Network for Internet of Things","authors":"Sudeshna Das, Abhishek Majumder, Suyel Namasudra, Ashish Singh","doi":"10.1111/exsy.13793","DOIUrl":"https://doi.org/10.1111/exsy.13793","url":null,"abstract":"<div>\u0000 \u0000 <p>Deep learning-based intrusion detection systems have high accuracy and low false alarm rates. However, there are challenges to deploy deep learning models in the vulnerable, resource-constrained Internet of Things. Therefore, two deep learning models are proposed: Lightweight Intrusion Detection System using Feedforward Neural Network (LIDSuFNN) and Lightweight Intrusion Detection System using Convolutional Neural Network (LIDSuCNN). In the models, the feedforward neural network is compressed using neuron pruning and the convolutional neural network is compressed using filter pruning. Then, quantization has been applied to the models. The models are trained and tested on standard datasets and synthetic datasets. A generative artificial intelligence model, Conditional Tabular Generative Adversarial Network (CTGAN), has been used to generate synthetic data. The models have been compared with the baselines and results are analyzed. Experimental results show that the proposed models require less training time and memory than the baselines, with approximately similar performance. The reduction of various parameters is due to the fact that pruning and quantization have removed unnecessary calculations from the networks. Statistical analysis has also been done to show the superiority of the proposed techniques.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117550","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}

引用次数: 0

RETRACTION: The Construction of Enterprise's Financial Supply Chain Management Under Blockchain Technology

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-19 DOI: 10.1111/exsy.13782

引用次数: 0

An Attention-Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-19 DOI: 10.1111/exsy.13791

Umesh Kumar Lilhore, Sarita Simaiya, Musaed Alhussein, Surjeet Dalal, Khursheed Aurangzeb, Amir Hussain

{"title":"An Attention-Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification","authors":"Umesh Kumar Lilhore, Sarita Simaiya, Musaed Alhussein, Surjeet Dalal, Khursheed Aurangzeb, Amir Hussain","doi":"10.1111/exsy.13791","DOIUrl":"https://doi.org/10.1111/exsy.13791","url":null,"abstract":"<div>\u0000 \u0000 <p>Heart disease continues to be a primary cause of mortality globally, highlighting the critical necessity for efficient early prediction and classification techniques. This study presents a new hybrid model attention-based CNN-Bi-LSTM that integrates the SMOTE with an attention-driven improved convolutional neural network-recurrent neural network architecture to improve the classification of heart sounds, especially from imbalanced datasets. Heart sounds are difficult to classify because of their complex acoustic properties and the variability of their characteristics across frequency and temporal domains. The proposed model utilises an advanced CNN to effectively extract global and local features, in conjunction with a bidirectional long short-term memory network to improve the architecture by capturing contextual information from both preceding and subsequent time sequences. The incorporation of spatial attention within the CNN and temporal attention in the RNN enables the model to concentrate on the most pertinent audio segments. To address the challenges presented by imbalanced and noisy datasets that may impede the efficacy of deep learning algorithms, our model employs SMOTE to improve data representation. The hybrid model outperformed popular models such as CNN, LSTM and CNN-LSTM, achieving a classification accuracy of more than 97% on the PCG and PASCAL heart sound datasets. The findings demonstrate the model's reliability as an initial evaluation tool in clinical settings, thereby improving support for cardiovascular disease diagnosis.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117326","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}

引用次数: 0

RETRACTION: Elstm: An Improved Long Short-term Memory Network Language Model for Sequence Learning

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-18 DOI: 10.1111/exsy.13795

引用次数: 0

RETRACTION: An Improved Differential Bond Energy Algorithm With Fuzzy Merging Method to Improve the Document Clustering for Information Mining

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-18 DOI: 10.1111/exsy.13797

引用次数: 0

RETRACTION: Cyber Security for Federated Learning Environment Using AI Technique

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-18 DOI: 10.1111/exsy.13794

引用次数: 0

Analysis of Different Modality of Data to Diagnose Parkinson's Disease Using Machine Learning and Deep Learning Approaches: A Review

IF 3 4区计算机科学

Expert Systems Pub Date : 2024-11-18 DOI: 10.1111/exsy.13790

Sheikh Bahauddin Arnab, Md Istakiak Adnan Palash, Rakibul Islam, Hemal Hossain Ovi, Mohammad Abu Yousuf, Md Zia Uddin

{"title":"Analysis of Different Modality of Data to Diagnose Parkinson's Disease Using Machine Learning and Deep Learning Approaches: A Review","authors":"Sheikh Bahauddin Arnab, Md Istakiak Adnan Palash, Rakibul Islam, Hemal Hossain Ovi, Mohammad Abu Yousuf, Md Zia Uddin","doi":"10.1111/exsy.13790","DOIUrl":"https://doi.org/10.1111/exsy.13790","url":null,"abstract":"<p>The dynamic nature of Parkinson's disease (PD) is that it gradually impacts regions of the brain that are responsible for the production of the dopamine hormone. Despite continuous efforts, no effective treatment or preventative approach exists for PD. Nonetheless, the disease can be detected. Our goal is to create a Machine Learning and Deep Learning-based system that can detect Parkinson's disease from a variety of data sources with high accuracy, sensitivity, specificity and interpretability. However, there have been significant advancements in the field of research, especially the use of artificial intelligence in the Parkinson's disease diagnostic process. We reviewed articles that were released between 2018 and 2024, concentrating on the most current studies that had been published. We chose 70 research articles for our review paper based on a set of criteria from a variety of online databases, including IEEExpress, medical databases like PubMed, Google Scholar, ResearchGate and ScienceDirect, and various publishers, including Elsevier, Taylor & Francis, Springer, MDPI, Plos One and so forth. According to our review, the majority of works make use of voice data. Our review study found that the highest accuracy level of most papers was above 90%, and the most commonly used algorithms were CNN and SVM. The main goal of this review study is to look into and put together information about the different ways that artificial intelligence, especially Machine Learning, can be used to find Parkinson's disease. Using diverse data gathered from multiple public and private datasets, we can infer that the application of artificial intelligence, particularly Machine Learning algorithms, for identifying Parkinson's disease plays a crucial role in the medical field.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.13790","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143116474","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}

引用次数: 0