Expert Systems最新文献

Unsupervised Deep Image Prior-Based Neural Networks for Single Image Super-Resolution: Comparative Analysis and Modelling Guidelines 用于单图像超分辨率的无监督深度图像先验神经网络：比较分析和建模指南

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-10-09 DOI: 10.1111/exsy.70142

Alejandra Abalo-García, Iván Ramírez, Emanuele Schiavi

{"title":"Unsupervised Deep Image Prior-Based Neural Networks for Single Image Super-Resolution: Comparative Analysis and Modelling Guidelines","authors":"Alejandra Abalo-García, Iván Ramírez, Emanuele Schiavi","doi":"10.1111/exsy.70142","DOIUrl":"https://doi.org/10.1111/exsy.70142","url":null,"abstract":"<p>Deep Image Prior (DIP) has been recently introduced as a method to exploit the structural priors inherent to neural networks. In the field of image processing, DIP effectively addresses various problems such as denoising, inpainting, image restoration and super-resolution. Unlike supervised neural networks, which require large amounts of labelled data, DIP operates as a single-image method, where prior knowledge is derived directly from the architecture of the neural network. In this work, we focus on the single-image super-resolution problem using DIP. Through extensive experiments for image super-resolution, we show that the original formulation of DIP can be improved by properly modelling fidelity with multiple down-sampling operators. Our experimental results systematically explore combinations of regularisation and fidelity terms across both hyperspectral and natural RGB image datasets, offering new guidelines for developing effective DIP-based approaches. Code and data are available at https://github.com/capo-urjc/dip-sisr.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70142","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272268","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

FastAGEDs+: Fast Approximate Graph Entity Dependency Discovery FastAGEDs+：快速近似图实体依赖关系发现

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-10-08 DOI: 10.1111/exsy.70152

Sibo Zhao, Guangtong Zhou, Selasi Kwashie, Michael Bewong, Vincent M. Nofong, Yidi Zhang, Junwei Hu, Li Qin, Zaiwen Feng

{"title":"FastAGEDs+: Fast Approximate Graph Entity Dependency Discovery","authors":"Sibo Zhao, Guangtong Zhou, Selasi Kwashie, Michael Bewong, Vincent M. Nofong, Yidi Zhang, Junwei Hu, Li Qin, Zaiwen Feng","doi":"10.1111/exsy.70152","DOIUrl":"https://doi.org/10.1111/exsy.70152","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper addresses the novel and challenging domain of graph entity dependencies (GEDs) discovery, which aims to identify dependencies in large graphs that are nearly satisfied despite the presence of errors, exceptions and ambiguities in real-world data. We propose a unique error measure specifically designed for GED semantics and innovatively adapts concepts of disagreement and necessary sets to the realm of graph dependencies. Furthermore, we introduce the <span>FastAGEDs+</span> algorithm, which significantly enhances efficiency in discovering approximate GEDs, employing a depth-first search strategy for optimal candidate space traversal. Incorporating an innovative pruning strategy, F<span>ast</span>AGEDs+ efficiently narrows down the search space, significantly reducing computational overhead while maintaining accuracy. Through extensive experimentation on real-world graphs, we demonstrate the feasibility and scalability of our approach, offering substantial improvements in data quality and management practices.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145271962","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

Time Series Embedding Methods for Classification Tasks: A Review 分类任务的时间序列嵌入方法综述

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-10-05 DOI: 10.1111/exsy.70148

Habib Irani, Yasamin Ghahremani, Arshia Kermani, Vangelis Metsis

{"title":"Time Series Embedding Methods for Classification Tasks: A Review","authors":"Habib Irani, Yasamin Ghahremani, Arshia Kermani, Vangelis Metsis","doi":"10.1111/exsy.70148","DOIUrl":"https://doi.org/10.1111/exsy.70148","url":null,"abstract":"<p>Time series analysis has become crucial in various fields, from engineering and finance to healthcare and social sciences. Due to their multidimensional nature, time series often need to be embedded into a fixed-dimensional feature space to enable processing with various machine learning algorithms. In this paper, we present a comprehensive review and quantitative evaluation of time series embedding methods for effective representations in machine learning and deep learning models. We introduce a taxonomy of embedding techniques, categorizing them based on their theoretical foundations and application contexts. Our work provides a quantitative evaluation of representative methods from each category by assessing their performance on downstream classification tasks across diverse real-world datasets. Our experimental results demonstrate that the performance of embedding methods varies significantly depending on the dataset and classification algorithm used, highlighting the importance of careful model selection and extensive experimentation for specific applications. This study contributes to the field by offering a systematic comparison of time series embedding techniques, guiding practitioners in selecting appropriate methods for their specific applications, and providing a foundation for future advancements in time series analysis. To facilitate further research and practical applications, we provide an open-source code repository implementing these embedding methods: https://github.com/imics-lab/time-series-embedding.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70148","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145271749","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

Re-Sampling Calibrated SNN Loss: A Robust Approach to Non-IID Data in Federated Learning 重新采样校准SNN损失：联邦学习中非iid数据的鲁棒方法

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-10-02 DOI: 10.1111/exsy.70145

Nathaniel Kang, Jongho Im

引用次数: 0

Sentiment Analysis on Memes: A Review 模因的情感分析综述

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-09-25 DOI: 10.1111/exsy.70133

Ravi Kumar Routhu, Ujwala Baruah

{"title":"Sentiment Analysis on Memes: A Review","authors":"Ravi Kumar Routhu, Ujwala Baruah","doi":"10.1111/exsy.70133","DOIUrl":"https://doi.org/10.1111/exsy.70133","url":null,"abstract":"<div>\u0000 \u0000 <p>This review explores the field of Sentiment Analysis on Memes, examining the methodologies employed to analyse the emotions expressed in widely shared online images. We discuss the various architectures used in sentiment analysis, review existing datasets and highlight shared tasks that facilitate model evaluation. The review also addresses the challenges specific to this domain, such as the interpretation of humour and sarcasm, which add complexity to sentiment analysis in the context of memes. A key focus of this review is the need for novel datasets that better capture the unique nature of memes, particularly those that blend text and images with cultural and emotional nuances. Existing benchmark datasets often fall short in representing the diversity of meme formats and regional variations, highlighting the necessity for more comprehensive datasets. Looking forward, we anticipate advancements in analytical methodologies and the development of such specialised datasets, which would significantly enhance the accuracy and depth of sentiment analysis models. This review serves as a comprehensive resource for researchers and practitioners interested in advancing the study of sentiment analysis in the evolving field of memes.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146422","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

Traversal Learning Coordination for Lossless and Efficient Distributed Learning 无损高效分布式学习的遍历学习协调

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-09-25 DOI: 10.1111/exsy.70141

Erdenebileg Batbaatar, Jeonggeol Kim, Yongcheol Kim, Young Yoon

{"title":"Traversal Learning Coordination for Lossless and Efficient Distributed Learning","authors":"Erdenebileg Batbaatar, Jeonggeol Kim, Yongcheol Kim, Young Yoon","doi":"10.1111/exsy.70141","DOIUrl":"https://doi.org/10.1111/exsy.70141","url":null,"abstract":"<p>In this paper, we introduce Traversal Learning (TL), a novel approach designed to address the problem of decreased quality encountered in popular distributed learning (DL) paradigms such as Federated Learning (FL), Split Learning (SL) and SplitFed Learning (SFL). Traditional FL often suffers an accuracy drop during aggregation due to its averaging function, while SL and SFL face increased loss due to the independent gradient updates on each split network. TL adopts a unique strategy where the model traverses the nodes during forward propagation (FP) and performs backward propagation (BP) at the orchestrator, effectively implementing centralised learning (CL) principles within a distributed environment. The orchestrator is tasked with generating virtual batches and planning the model's sequential node visits during FP, aligning them with the ordered index of the data within these batches. We conducted experiments on six datasets representing diverse characteristics across various domains. Our evaluation demonstrates that TL is on par with classic CL approaches in terms of accurate inference, thereby offering a viable and robust solution for DL tasks. TL outperformed other DL methods and improved accuracy by 7.85% for independent and identically distributed (IID) datasets, macro F1-score by 1.06% for non-IID datasets, accuracy by 2.05% for text classification and AUC by 1.41% and 2.82% for medical and financial datasets, respectively. By effectively preserving data privacy while maintaining performance, TL represents a significant advancement in DL methodologies.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70141","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146421","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

Twitter and Sentiment Analysis for Wildfire Heat Mapping 野火热图的Twitter和情感分析

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-09-25 DOI: 10.1111/exsy.70147

Catarina Silva, Isabel Carvalho, Bruno Ferreira, João Cabral Pinto, Alberto Cardoso, Hugo Gonçalo Oliveira

{"title":"Twitter and Sentiment Analysis for Wildfire Heat Mapping","authors":"Catarina Silva, Isabel Carvalho, Bruno Ferreira, João Cabral Pinto, Alberto Cardoso, Hugo Gonçalo Oliveira","doi":"10.1111/exsy.70147","DOIUrl":"https://doi.org/10.1111/exsy.70147","url":null,"abstract":"<p>Nowadays, automated intelligent systems play an increasingly vital role in aiding decision-making processes across various fields. Firefighting represents a crucial area where accurate information gathering is paramount for efficient resource allocation. Social media platforms as Twitter (or X) have emerged as valuable sources of real-time data, often referred to as ‘citizen science’, offering additional insights alongside traditional data sources. In this work, we introduce a novel pipeline that leverages Natural Language Processing (NLP) techniques and Twitter data, utilising transformer models to identify and monitor wildfire incidents. Expanding on this approach, we incorporate sentiment analysis to provide deeper insights into public perceptions and emotions related to fire events. Additionally, we present visual representations of geographic data through heat mapping, potentially aiding firefighters in making informed decisions. By integrating advanced NLP techniques with social media data, our approach presents a promising strategy for enhancing wildfire management efforts.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70147","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146509","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 Overview of Q-Learning and Deep Q-Learning for an Autonomous Multi-UAV Wireless Network 自主多无人机无线网络的q -学习和深度q -学习综述

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-09-24 DOI: 10.1111/exsy.70143

Vikash Chandra Sharma, Saugata Roy

{"title":"An Overview of Q-Learning and Deep Q-Learning for an Autonomous Multi-UAV Wireless Network","authors":"Vikash Chandra Sharma, Saugata Roy","doi":"10.1111/exsy.70143","DOIUrl":"https://doi.org/10.1111/exsy.70143","url":null,"abstract":"<div>\u0000 \u0000 <p>In various fields, including environmental monitoring, communication, surveillance, and disaster response, unmanned aerial vehicles (UAVs) are increasingly essential. Autonomous multi-UAV wireless networks (MUWNs), where multiple UAVs work together, offer powerful solutions in these fields. However, making these networks fully autonomous is challenging, especially concerning real-time decision-making, coordination, and resource management. In the field of literature, there is a demand for a comprehensive survey of recent developments in Q-learning (QL) and deep Q-learning (DQL) within MUWNs. To address this gap, we provide a thorough evaluation of QL and DQL approaches, focusing on their application in autonomous MUWNs. We highlight their roles in route planning, communication relays, and network optimization, discussing advantages and limitations. The survey also explores key challenges, including scalability, energy efficiency, and real-time adaptability, and reviews how QL/DQL enhancements address them. In particular, this paper provides an overview of some QL and DQL applications in MUWNs, such as data retrieval, monitoring, aggregation, resource allocation, and task scheduling to support wireless connectivity, UAV-assisted autonomous trajectory planning, navigation, security, and jamming avoidance. The use of these technologies enables the effective use of UAVs in smart cities, monitoring of industrial complexes, agricultural surveys, and border security. Additionally, using the knowledge gathered from our review, we identify and discuss several open challenges.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146536","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

Emotional Climate Recognition in Speech-Based Conversations: Leveraging Deep Bispectral Image Analysis and Affect Dynamics 基于语音的对话中的情绪气候识别：利用深度双谱图像分析和影响动力学

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-09-23 DOI: 10.1111/exsy.70146

Ghada Alhussein, Mohanad Alkhodari, Shiza Saleem, Ahsan H. Khandoker, Leontios J. Hadjileontiadis

{"title":"Emotional Climate Recognition in Speech-Based Conversations: Leveraging Deep Bispectral Image Analysis and Affect Dynamics","authors":"Ghada Alhussein, Mohanad Alkhodari, Shiza Saleem, Ahsan H. Khandoker, Leontios J. Hadjileontiadis","doi":"10.1111/exsy.70146","DOIUrl":"https://doi.org/10.1111/exsy.70146","url":null,"abstract":"<p>The growing availability of conversational data across multiple platforms has intensified interest in dynamic emotion recognition. Speech plays a pivotal role in shaping the emotional climate (EC) of peer conversations. We propose DeepBispec, the first framework to integrate deep bispectral image analysis with affect dynamics (AD) for speech-based EC recognition. Bispectrum representations capture nonlinear and non-Gaussian speech characteristics, while AD descriptors model temporal emotion fluctuations. Evaluated on K-EmoCon, IEMOCAP and SEWA datasets, DeepBispec consistently improved EC classification performance. For example, on K-EmoCon, arousal accuracy increased from 79.0% (bispectrum only) to 81.4% (with AD), while valence accuracy improved from 76.8% to 77.5%; similar trends were observed for IEMOCAP and SEWA. DeepBispec outperformed strong CNN, LSTM, and Transformer baselines, demonstrating robust cross-lingual performance across seven languages. These findings highlight its potential for real-world applications such as mental health monitoring, affect-aware learning platforms and empathetic dialogue systems.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70146","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146313","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

Continuous Time Markov Chain for Smartwatch Sensors 智能手表传感器的连续时间马尔可夫链

IF 2.3 4区计算机科学

Expert Systems Pub Date : 2025-09-23 DOI: 10.1111/exsy.70144

Iti Chaturvedi, Wei Liang Seow, Amber Hogarth, Luca Adornetto, Erik Cambria

{"title":"Continuous Time Markov Chain for Smartwatch Sensors","authors":"Iti Chaturvedi, Wei Liang Seow, Amber Hogarth, Luca Adornetto, Erik Cambria","doi":"10.1111/exsy.70144","DOIUrl":"https://doi.org/10.1111/exsy.70144","url":null,"abstract":"<p>Time-series forecasting is essential for predicting events in the future and for tracking objects. The conventional recurrent neural network model needs to pad the target with zeros when handling long inputs, resulting in a loss in accuracy. Recently, it was proposed to divide a time series input into patches and merge the learned weights. However, such a model is difficult to interpret. In this article, we consider a mixture of continuous and discrete Markov states to model long-range time dependencies. For example, in a vehicle, each gear level can be a discrete state and the throttle input is continuously controlled to maximise the efficiency of the engine. Data collected from the sensor is prone to noise due to component faults or external disturbances. Hence, we apply a stability constraint to select samples for training. We validate our algorithm on three datasets: (1) Apple Watch, (2) Car engine and (3) Election tweets. On all datasets, we achieve an improvement in the range of 5%–20% in the F-measure. Furthermore, the features learned are easy to explain in terms of real-world scenarios.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 11","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70144","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146312","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