Pub Date : 2025-11-10DOI: 10.1016/j.iswa.2025.200607
Jake Street, Isibor Kennedy Ihianle, Funminiyi Olajide, Ahmad Lotfi
Online Grooming (OG) is a prevalent threat facing predominately children online, with groomers using deceptive methods to prey on the vulnerability of children on social media/messaging platforms. These attacks can have severe psychological and physical impacts, including a tendency towards revictimization. Current technical measures are inadequate, especially with the advent of end-to-end encryption which hampers message monitoring. Existing solutions focus on the signature analysis of child abuse media, which does not effectively address real-time OG detection. This paper proposes that OG attacks are complex, requiring the identification of specific communication patterns between adults and children alongside identifying other insights (e.g. Sexual language) to make an accurate determination. It introduces a novel approach leveraging advanced models such as BERT and RoBERTa for Message-Level Analysis and a Context Determination approach for classifying actor interactions, between adults attempting to groom children and honeypot children actors. This approach included the introduction of Actor Significance Thresholds and Message Significance Thresholds to make these determinations. The proposed method aims to enhance accuracy and robustness in detecting OG by considering the dynamic and multi-faceted nature of these attacks. Cross-dataset experiments evaluate the robustness and versatility of our approach. This paper’s contributions include improved detection methodologies and the potential for application in various scenarios, addressing gaps in current literature and practices.
{"title":"Enhanced Online Grooming detection employing Context Determination and Message-Level Analysis","authors":"Jake Street, Isibor Kennedy Ihianle, Funminiyi Olajide, Ahmad Lotfi","doi":"10.1016/j.iswa.2025.200607","DOIUrl":"10.1016/j.iswa.2025.200607","url":null,"abstract":"<div><div>Online Grooming (OG) is a prevalent threat facing predominately children online, with groomers using deceptive methods to prey on the vulnerability of children on social media/messaging platforms. These attacks can have severe psychological and physical impacts, including a tendency towards revictimization. Current technical measures are inadequate, especially with the advent of end-to-end encryption which hampers message monitoring. Existing solutions focus on the signature analysis of child abuse media, which does not effectively address real-time OG detection. This paper proposes that OG attacks are complex, requiring the identification of specific communication patterns between adults and children alongside identifying other insights (e.g. Sexual language) to make an accurate determination. It introduces a novel approach leveraging advanced models such as BERT and RoBERTa for Message-Level Analysis and a Context Determination approach for classifying actor interactions, between adults attempting to groom children and honeypot children actors. This approach included the introduction of Actor Significance Thresholds and Message Significance Thresholds to make these determinations. The proposed method aims to enhance accuracy and robustness in detecting OG by considering the dynamic and multi-faceted nature of these attacks. Cross-dataset experiments evaluate the robustness and versatility of our approach. This paper’s contributions include improved detection methodologies and the potential for application in various scenarios, addressing gaps in current literature and practices.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200607"},"PeriodicalIF":4.3,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145520070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper surveys the different approaches in semantic Simultaneous Localization and Mapping (SLAM), exploring how the incorporation of semantic information has enhanced performance in both indoor and outdoor settings, while highlighting key advancements in the field. It also identifies existing gaps and proposes potential directions for future improvements to address these issues. We provide a detailed review of the fundamentals of semantic SLAM, illustrating how incorporating semantic data enhances scene understanding and mapping accuracy. The paper presents semantic SLAM methods and core techniques that contribute to improved robustness and precision in mapping. A comprehensive overview of commonly used datasets for evaluating semantic SLAM systems is provided, along with a discussion of performance metrics used to assess their efficiency and accuracy. To demonstrate the reliability of semantic SLAM methodologies, we reproduce selected results from existing studies offering insights into the reproducibility of these approaches. The paper also addresses key challenges such as real-time processing, dynamic scene adaptation, and scalability while highlighting future research directions. Unlike prior surveys, this paper uniquely combines (i) a systematic taxonomy of semantic SLAM approaches across different sensing modalities and environments, (ii) a comparative review of datasets and evaluation metrics, and (iii) a reproducibility study of selected methods. To our knowledge, this is the first survey that integrates methods, datasets, evaluation practices, and application insights into a single comprehensive review, thereby offering a unified reference for researchers and practitioners. In conclusion, this review underscores the vital role of semantic SLAM in driving advancements in autonomous systems and intelligent navigation by analyzing recent developments, validating findings, and highlighting future research directions.
{"title":"Semantic SLAM: A comprehensive survey of methods and applications","authors":"Houssein Kanso , Abhilasha Singh , Etaf El Zarif , Nooruldeen Almohammed , Jinane Mounsef , Noel Maalouf , Bilal Arain","doi":"10.1016/j.iswa.2025.200591","DOIUrl":"10.1016/j.iswa.2025.200591","url":null,"abstract":"<div><div>This paper surveys the different approaches in semantic Simultaneous Localization and Mapping (SLAM), exploring how the incorporation of semantic information has enhanced performance in both indoor and outdoor settings, while highlighting key advancements in the field. It also identifies existing gaps and proposes potential directions for future improvements to address these issues. We provide a detailed review of the fundamentals of semantic SLAM, illustrating how incorporating semantic data enhances scene understanding and mapping accuracy. The paper presents semantic SLAM methods and core techniques that contribute to improved robustness and precision in mapping. A comprehensive overview of commonly used datasets for evaluating semantic SLAM systems is provided, along with a discussion of performance metrics used to assess their efficiency and accuracy. To demonstrate the reliability of semantic SLAM methodologies, we reproduce selected results from existing studies offering insights into the reproducibility of these approaches. The paper also addresses key challenges such as real-time processing, dynamic scene adaptation, and scalability while highlighting future research directions. Unlike prior surveys, this paper uniquely combines (i) a systematic taxonomy of semantic SLAM approaches across different sensing modalities and environments, (ii) a comparative review of datasets and evaluation metrics, and (iii) a reproducibility study of selected methods. To our knowledge, this is the first survey that integrates methods, datasets, evaluation practices, and application insights into a single comprehensive review, thereby offering a unified reference for researchers and practitioners. In conclusion, this review underscores the vital role of semantic SLAM in driving advancements in autonomous systems and intelligent navigation by analyzing recent developments, validating findings, and highlighting future research directions.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200591"},"PeriodicalIF":4.3,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Current research in radiology report generation tend to overlook the utilization of abnormalities depicted in medical images. This study introduces a novel radiology report generator that integrates a multi-label learning approach for predicting abnormality tags and employs transformer models for generating reports. Additionally, the research explores contrast-based image enhancement to mitigate noise in medical images, evaluating its impact on model performance. The multi-label learning is trained on a dataset with 180 abnormality labels and the features used as initial weights for MIMICCXR, as a visual feature extractor.Imbalance handling and ensemble methods are employed to optimize multi-label model performance for abnormality tag prediction. Multi-head attention, in conjunction with GPT-2, facilitates context building for medical report generation, utilizing BERT embeddings for text feature extraction. Evaluation metrics demonstrate that the proposed model achieves superior performance in both multi-label prediction accuracy 77 % and text generation, showing an increase in similarity 28 % in average compared to the baseline model. These findings suggest that leveraging transfer learning with an ensemble classifier, combined with a transformer for context building and decoding, effectively utilizes visual and text features. Furthermore, the incorporation of image enhancement techniques significantly impacts model performance.
{"title":"Enhanced radiology report: Leveraging image enhancement and multi-label transfer learning with attention-based text generation","authors":"Hilya Tsaniya , Chastine Fatichah , Nanik Suciati , Takashi Obi , Joong-sun Lee","doi":"10.1016/j.iswa.2025.200605","DOIUrl":"10.1016/j.iswa.2025.200605","url":null,"abstract":"<div><div>Current research in radiology report generation tend to overlook the utilization of abnormalities depicted in medical images. This study introduces a novel radiology report generator that integrates a multi-label learning approach for predicting abnormality tags and employs transformer models for generating reports. Additionally, the research explores contrast-based image enhancement to mitigate noise in medical images, evaluating its impact on model performance. The multi-label learning is trained on a dataset with 180 abnormality labels and the features used as initial weights for MIMIC<img>CXR, as a visual feature extractor.Imbalance handling and ensemble methods are employed to optimize multi-label model performance for abnormality tag prediction. Multi-head attention, in conjunction with GPT-2, facilitates context building for medical report generation, utilizing BERT embeddings for text feature extraction. Evaluation metrics demonstrate that the proposed model achieves superior performance in both multi-label prediction accuracy 77 % and text generation, showing an increase in similarity 28 % in average compared to the baseline model. These findings suggest that leveraging transfer learning with an ensemble classifier, combined with a transformer for context building and decoding, effectively utilizes visual and text features. Furthermore, the incorporation of image enhancement techniques significantly impacts model performance.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200605"},"PeriodicalIF":4.3,"publicationDate":"2025-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145520078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-08DOI: 10.1016/j.iswa.2025.200601
Rim El Badaoui , Ester Bonmati , Vasileios Argyriou , Barbara Villarini
Deep learning for medical imaging has shown great potential in improving patient outcomes due to its high accuracy in disease diagnosis. However, a major challenge preventing the widespread adoption of such models in clinical settings is data accessibility, which conflicts with the General Data Protection Regulation (GDPR) in a traditional centralised training environment. Hence, to address this issue, Federated Learning (FL) was introduced as a decentralised alternative that enables collaborative model training among data owners without sharing any private data. Despite its significance in healthcare, limited research has explored FL for medical imaging, particularly in multimodal brain tumour segmentation, due to challenges such as data heterogeneity.
In this study, we present Federated E-CATBraTS, an advanced federated deep learning model derived from the existing E-CATBraTS framework. This model is designed to segment brain tumours from multimodal magnetic resonance imaging (MRI) while preserving data privacy. Our framework introduces a novel aggregation method, DaQAvg, which optimally combines model weights based on data size and quality, demonstrating resilience against corrupted medical images.
We evaluated the performance of Federated E-CATBraTS using two publicly available datasets: UPenn-GBM and UCSF-PDGM, including a degraded version of the latter to assess the efficacy of our aggregation method. The results indicate a 6% overall improvement over traditional centralised approaches. Furthermore, we conducted a comprehensive comparison against state-of-the-art FL aggregation algorithms, including FedAVG, FedProx and FedNova. While FedNova demonstrated the highest overall DSC, DaQAvg demonstrated superior robustness to noisy conditions, showcasing its specific advantage in maintaining performance with variable data quality, a critical aspect in medical imaging.
{"title":"Federated learning using quality-based aggregation method for brain tumour segmentation on multimodality medical images","authors":"Rim El Badaoui , Ester Bonmati , Vasileios Argyriou , Barbara Villarini","doi":"10.1016/j.iswa.2025.200601","DOIUrl":"10.1016/j.iswa.2025.200601","url":null,"abstract":"<div><div>Deep learning for medical imaging has shown great potential in improving patient outcomes due to its high accuracy in disease diagnosis. However, a major challenge preventing the widespread adoption of such models in clinical settings is data accessibility, which conflicts with the General Data Protection Regulation (GDPR) in a traditional centralised training environment. Hence, to address this issue, Federated Learning (FL) was introduced as a decentralised alternative that enables collaborative model training among data owners without sharing any private data. Despite its significance in healthcare, limited research has explored FL for medical imaging, particularly in multimodal brain tumour segmentation, due to challenges such as data heterogeneity.</div><div>In this study, we present Federated E-CATBraTS, an advanced federated deep learning model derived from the existing E-CATBraTS framework. This model is designed to segment brain tumours from multimodal magnetic resonance imaging (MRI) while preserving data privacy. Our framework introduces a novel aggregation method, DaQAvg, which optimally combines model weights based on data size and quality, demonstrating resilience against corrupted medical images.</div><div>We evaluated the performance of Federated E-CATBraTS using two publicly available datasets: UPenn-GBM and UCSF-PDGM, including a degraded version of the latter to assess the efficacy of our aggregation method. The results indicate a 6% overall improvement over traditional centralised approaches. Furthermore, we conducted a comprehensive comparison against state-of-the-art FL aggregation algorithms, including FedAVG, FedProx and FedNova. While FedNova demonstrated the highest overall DSC, DaQAvg demonstrated superior robustness to noisy conditions, showcasing its specific advantage in maintaining performance with variable data quality, a critical aspect in medical imaging.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200601"},"PeriodicalIF":4.3,"publicationDate":"2025-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145520079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-07DOI: 10.1016/j.iswa.2025.200604
Tiago Jacob Fernandes França , José Henrique Pereira São Mamede , João Manuel Pereira Barroso , Vítor Manuel Pereira Duarte dos Santos
The rapid evolution of Artificial Intelligence (AI) is reshaping Human Resource Management (HRM), with growing interest in its role in talent identification. While AI has demonstrated effectiveness in analysing structured data, its limitations in assessing qualitative attributes such as creativity, adaptability, and emotional intelligence remain underexplored. This study addresses these gaps through an exploratory mixed-methods design, combining a global survey (n = 240) with semi-structured interviews of HR professionals. Quantitative analysis highlights patterns of association between key competencies, while qualitative findings provide contextual insights into perceptions of fairness, bias, and cultural resistance. The results suggest that AI can complement, but not replace, human judgement, supporting a Hybrid Evaluative Model that integrates algorithmic efficiency with human interpretation. The study contributes rare empirical evidence to a nascent field, highlights the ethical imperatives of bias mitigation and transparency, and underscores the importance of cultural context (collectivist versus individualist orientations) in shaping the acceptance and effectiveness of AI-enabled HR practices. These findings offer practical guidance for organisations and advance theory-building at the intersection of AI and HRM.
{"title":"Beyond algorithms: Artificial intelligence driven talent identification with human insight","authors":"Tiago Jacob Fernandes França , José Henrique Pereira São Mamede , João Manuel Pereira Barroso , Vítor Manuel Pereira Duarte dos Santos","doi":"10.1016/j.iswa.2025.200604","DOIUrl":"10.1016/j.iswa.2025.200604","url":null,"abstract":"<div><div>The rapid evolution of Artificial Intelligence (AI) is reshaping Human Resource Management (HRM), with growing interest in its role in talent identification. While AI has demonstrated effectiveness in analysing structured data, its limitations in assessing qualitative attributes such as creativity, adaptability, and emotional intelligence remain underexplored. This study addresses these gaps through an exploratory mixed-methods design, combining a global survey (<em>n</em> = 240) with semi-structured interviews of HR professionals. Quantitative analysis highlights patterns of association between key competencies, while qualitative findings provide contextual insights into perceptions of fairness, bias, and cultural resistance. The results suggest that AI can complement, but not replace, human judgement, supporting a Hybrid Evaluative Model that integrates algorithmic efficiency with human interpretation. The study contributes rare empirical evidence to a nascent field, highlights the ethical imperatives of bias mitigation and transparency, and underscores the importance of cultural context (collectivist versus individualist orientations) in shaping the acceptance and effectiveness of AI-enabled HR practices. These findings offer practical guidance for organisations and advance theory-building at the intersection of AI and HRM.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200604"},"PeriodicalIF":4.3,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-07DOI: 10.1016/j.iswa.2025.200606
Bronagh Lanigan , Zeinab Rezaeifar , Federico Cruciani , Michael Milliken , Jordan Vincent , Samuel Moore , Muhammad Aaqib , Alan Mills , Pushpinder K. Chouhan , Alfie Beard , Chris D. Nugent , Luke Chen , Alex Healing
With the increasing diversity of IoT devices, keeping IT systems secure is becoming increasingly difficult. Attackers exploit vulnerabilities within the system in order to access sensitive information, typically reaching their objective through several steps. Current Intrusion Detection Systems (IDSs) focus on low-level alerts, and tend to produce a high rate of false positives. This type of information alone is insufficient for the detection of sophisticated attack scenarios such Advanced Persistent Threats (APTs). Consequently, correlation techniques have recently been introduced to correlate alerts and reconstruct attack scenarios, however, various attack scenarios exist, with diverse characteristics. Also, different steps of the APTs scenarios may have their own characteristics. Therefore, finding a proper method that covers all cases remains a challenge. Moreover, after detecting APTs, how the system should respond to these attacks to avoid sabotage to the system remains a challenge. Thus, in this paper, first for detection of the attacks, we classify different cases, and then, a method based on different characteristics of attack patterns is proposed to detect APT scenarios. The proposed method consists of two main phases: APT detection and the intelligent hybrid response framework. In APT detection phase, similar alerts are aggregated and attack graphs are generated based on a similarity matrix. These graphs, combined with third party API data enable alert correlation and APT scenario detection. Entity graphs are then created to visualise host behaviour, and alert graphs are analysed to detect APT scenarios. In the response phase, attack graphs produced from the correlation inform the hybrid response framework, integrating knowledge and data-driven components that facilitate automated or recommended mitigation. The approach was evaluated on the ZeekData24 dataset. Obtained precision and recall on the malicious traffic was observed to be 96.65% and 87.04% respectively. The results show that our approach can effectively filter false positive alerts with a reduction of the data going from 10,063 alerts daily to 586 meta-alerts, pruned to 48 attack graphs and finally reduced to 20 suspicious attack graphs.
{"title":"Alert correlation for intelligent threat detection and response","authors":"Bronagh Lanigan , Zeinab Rezaeifar , Federico Cruciani , Michael Milliken , Jordan Vincent , Samuel Moore , Muhammad Aaqib , Alan Mills , Pushpinder K. Chouhan , Alfie Beard , Chris D. Nugent , Luke Chen , Alex Healing","doi":"10.1016/j.iswa.2025.200606","DOIUrl":"10.1016/j.iswa.2025.200606","url":null,"abstract":"<div><div>With the increasing diversity of IoT devices, keeping IT systems secure is becoming increasingly difficult. Attackers exploit vulnerabilities within the system in order to access sensitive information, typically reaching their objective through several steps. Current Intrusion Detection Systems (IDSs) focus on low-level alerts, and tend to produce a high rate of false positives. This type of information alone is insufficient for the detection of sophisticated attack scenarios such Advanced Persistent Threats (APTs). Consequently, correlation techniques have recently been introduced to correlate alerts and reconstruct attack scenarios, however, various attack scenarios exist, with diverse characteristics. Also, different steps of the APTs scenarios may have their own characteristics. Therefore, finding a proper method that covers all cases remains a challenge. Moreover, after detecting APTs, how the system should respond to these attacks to avoid sabotage to the system remains a challenge. Thus, in this paper, first for detection of the attacks, we classify different cases, and then, a method based on different characteristics of attack patterns is proposed to detect APT scenarios. The proposed method consists of two main phases: APT detection and the intelligent hybrid response framework. In APT detection phase, similar alerts are aggregated and attack graphs are generated based on a similarity matrix. These graphs, combined with third party API data enable alert correlation and APT scenario detection. Entity graphs are then created to visualise host behaviour, and alert graphs are analysed to detect APT scenarios. In the response phase, attack graphs produced from the correlation inform the hybrid response framework, integrating knowledge and data-driven components that facilitate automated or recommended mitigation. The approach was evaluated on the ZeekData24 dataset. Obtained precision and recall on the malicious traffic was observed to be 96.65% and 87.04% respectively. The results show that our approach can effectively filter false positive alerts with a reduction of the data going from 10,063 alerts daily to 586 meta-alerts, pruned to 48 attack graphs and finally reduced to 20 suspicious attack graphs.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200606"},"PeriodicalIF":4.3,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145520065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-07DOI: 10.1016/j.iswa.2025.200599
Maikel Leon
This study provides a comprehensive review of two decades of research in opinion mining and sentiment analysis, addressing the fragmentation of prior work across methodologies, application domains, and data sources. The evolution of the field is traced from pre-1990 rule-based systems to lexicon heuristics, statistical learning, machine learning, deep learning, and the current wave of transformer-driven, multimodal, and generative models. Applications are examined across marketing, finance, politics, and social media, with emphasis on how methodological innovations have improved accuracy and enabled broader adoption. Best practices – including transformer fine-tuning, prompt engineering, zero-shot and few-shot learning, multimodal fusion, and domain adaptation – are analyzed to distill evidence-based guidelines for researchers and practitioners. The synthesis shows how sentiment analysis has shaped critical areas, including brand management, investor decision-making, political discourse, and online user engagement. Findings highlight the effectiveness of transformer-based approaches, particularly when combined with domain adaptation and prompt engineering, in delivering state-of-the-art performance. Beyond methodological and applied insights, the study identifies promising directions for future research, including real-time customer journey analytics, explainability in generative AI, robustness across multiple languages, ethical implications, and sustainability considerations. By consolidating dispersed knowledge into a unified account, this review provides both historical grounding and a structured roadmap that advances theoretical understanding and informs managerial practice.
{"title":"Sentiment analysis: From rule-based lexicons to large language models","authors":"Maikel Leon","doi":"10.1016/j.iswa.2025.200599","DOIUrl":"10.1016/j.iswa.2025.200599","url":null,"abstract":"<div><div>This study provides a comprehensive review of two decades of research in opinion mining and sentiment analysis, addressing the fragmentation of prior work across methodologies, application domains, and data sources. The evolution of the field is traced from pre-1990 rule-based systems to lexicon heuristics, statistical learning, machine learning, deep learning, and the current wave of transformer-driven, multimodal, and generative models. Applications are examined across marketing, finance, politics, and social media, with emphasis on how methodological innovations have improved accuracy and enabled broader adoption. Best practices – including transformer fine-tuning, prompt engineering, zero-shot and few-shot learning, multimodal fusion, and domain adaptation – are analyzed to distill evidence-based guidelines for researchers and practitioners. The synthesis shows how sentiment analysis has shaped critical areas, including brand management, investor decision-making, political discourse, and online user engagement. Findings highlight the effectiveness of transformer-based approaches, particularly when combined with domain adaptation and prompt engineering, in delivering state-of-the-art performance. Beyond methodological and applied insights, the study identifies promising directions for future research, including real-time customer journey analytics, explainability in generative AI, robustness across multiple languages, ethical implications, and sustainability considerations. By consolidating dispersed knowledge into a unified account, this review provides both historical grounding and a structured roadmap that advances theoretical understanding and informs managerial practice.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200599"},"PeriodicalIF":4.3,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deep Neural Networks (DNNs) are highly vulnerable to disruptions caused by minimal noise, yet research on physical attacks leveraging light-based methods remains scarce. Light-based physical attacks are exceptionally stealthy, posing substantial security threats to vision-dependent applications such as autonomous driving. This paper enhances a state-of-the-art light-based physical attack that employs a genetic algorithm to optimize laser spot placement for maximum effectiveness. We expand the algorithm by introducing additional hyperparameters and systematically optimizing them to establish the most efficient workflow for this problem. To our knowledge, this is the first light-based attack capable of reliably performing physical attacks during daylight conditions, making it the most effective and robust approach of its kind. Extensive experiments conducted in a digital environment demonstrate the superiority of the genetic algorithm over random-location methods. By identifying optimal hyperparameter values, we achieve significant improvements in both performance and efficiency. Specifically, we managed to achieve an Attack Success Rate (ASR) of 89.7%, with an Average Query (AQ) of only 109.4, demonstrating a highly efficient and effective approach. The results reveal that laser spots can severely interfere with advanced DNNs, highlighting the critical security risks associated with this technique.
{"title":"Comprehensive analysis on laser spots adversarial attacks using genetic algorithm","authors":"Youssef Mansour , Ayad Turky , Ibrahim Abaker Hashem , Imad Afyouni , Ali Bou Nassif , Ismail Shahin , Ashraf Elnagar","doi":"10.1016/j.iswa.2025.200598","DOIUrl":"10.1016/j.iswa.2025.200598","url":null,"abstract":"<div><div>Deep Neural Networks (DNNs) are highly vulnerable to disruptions caused by minimal noise, yet research on physical attacks leveraging light-based methods remains scarce. Light-based physical attacks are exceptionally stealthy, posing substantial security threats to vision-dependent applications such as autonomous driving. This paper enhances a state-of-the-art light-based physical attack that employs a genetic algorithm to optimize laser spot placement for maximum effectiveness. We expand the algorithm by introducing additional hyperparameters and systematically optimizing them to establish the most efficient workflow for this problem. To our knowledge, this is the first light-based attack capable of reliably performing physical attacks during daylight conditions, making it the most effective and robust approach of its kind. Extensive experiments conducted in a digital environment demonstrate the superiority of the genetic algorithm over random-location methods. By identifying optimal hyperparameter values, we achieve significant improvements in both performance and efficiency. Specifically, we managed to achieve an Attack Success Rate (ASR) of 89.7%, with an Average Query (AQ) of only 109.4, demonstrating a highly efficient and effective approach. The results reveal that laser spots can severely interfere with advanced DNNs, highlighting the critical security risks associated with this technique.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200598"},"PeriodicalIF":4.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-31DOI: 10.1016/j.iswa.2025.200597
Ramen Ghosh
Ensuring hard constraint satisfaction during both training and deployment is central to safety-critical reinforcement learning (RL). Control-theoretic regularization (CTR) enforces safety by filtering actions through viability- or barrier-certified safe sets, but evaluating the state-dependent regulator online is often prohibitive in high dimensions. We propose a scalable CTR framework based on neural regulator approximators —differentiable surrogates of that enable fast projection or rejection-sampling filters within standard RL loops. We formalize a learning-theoretic analysis for approximate safety filtering and prove probably approximately correct (PAC)-style guarantees: if the set approximation error is bounded by with confidence , then the probability of constraint violation along a length– rollout is bounded by a term that scales linearly in and (plus ). We further show that the performance suboptimality of the filtered policy is controlled analytically by the same approximation envelope, yielding an explicit, provably quantified safety-versus-optimality tradeoff (PAC bounds linear in and the envelope), complemented by empirical ablations; see also the calculus-of-variations view of constrained tradeoffs (Younis, 2023). The resulting method, CTR-Net, is architecture-agnostic and supports real-time execution via fast, differentiable safety layers. Empirical evaluations on high-dimensional continuous-control benchmarks — including safe locomotion and constrained multi-joint manipulation — demonstrate reliable constraint satisfaction during learning and deployment, robustness under modeling uncertainty and substantial computational gains relative to exact viability/barrier baselines. By coupling operator-free neural safety sets with CTR guarantees, CTR-Net bridges theoretical safety certificates and scalable implementation, advancing practical, real-time safe RL for complex intelligent systems.
在训练和部署期间确保硬约束的满足是安全关键型强化学习（RL）的核心。控制理论正则化（CTR）通过生存能力或障碍认证的安全集过滤动作来加强安全性，但是在线评估状态相关的调节器R(x)在高维中通常是令人望而却步的。我们提出了一个可扩展的CTR框架，该框架基于神经调节器近似器R θ(x) - R(x)的可微替代品，可以在标准RL环路内实现快速投影或拒绝采样滤波器。我们形式化了近似安全过滤的学习理论分析，并证明了可能近似正确（PAC）风格的保证：如果集合近似误差以置信度为1−δ的π为界，那么沿长度- T rollout的约束违反概率由一个在T和π (+ δ)中线性缩放的项为界。我们进一步表明，过滤策略的性能次优性由相同的近似包络分析控制，产生明确的，可证明的量化安全与最优性权衡（PAC界在T和包络中是线性的），辅以经验消融；另见约束权衡的变分演算观点（Younis, 2023）。由此产生的方法cnet与体系结构无关，并通过快速、可区分的安全层支持实时执行。对高维连续控制基准（包括安全运动和约束多关节操作）的经验评估表明，在学习和部署过程中，约束满足是可靠的，建模不确定性下的鲁棒性和相对于确切的可行性/障碍基线的大量计算收益。通过将无操作人员的神经安全集与CTR保证相结合，CTR- net将理论安全证书与可扩展的实施相结合，为复杂的智能系统推进实用、实时的安全RL。
{"title":"CTR-Net: Scalable safe reinforcement learning via neural approximations of control theoretic regulators","authors":"Ramen Ghosh","doi":"10.1016/j.iswa.2025.200597","DOIUrl":"10.1016/j.iswa.2025.200597","url":null,"abstract":"<div><div>Ensuring hard constraint satisfaction during both training and deployment is central to safety-critical reinforcement learning (RL). Control-theoretic regularization (CTR) enforces safety by filtering actions through viability- or barrier-certified safe sets, but evaluating the state-dependent regulator <span><math><mrow><mi>R</mi><mrow><mo>(</mo><mi>x</mi><mo>)</mo></mrow></mrow></math></span> online is often prohibitive in high dimensions. We propose a scalable CTR framework based on <em>neural regulator approximators</em> <span><math><mrow><msub><mrow><mover><mrow><mi>R</mi></mrow><mrow><mo>ˆ</mo></mrow></mover></mrow><mrow><mi>θ</mi></mrow></msub><mrow><mo>(</mo><mi>x</mi><mo>)</mo></mrow></mrow></math></span>—differentiable surrogates of <span><math><mrow><mi>R</mi><mrow><mo>(</mo><mi>x</mi><mo>)</mo></mrow></mrow></math></span> that enable fast projection or rejection-sampling filters within standard RL loops. We formalize a learning-theoretic analysis for approximate safety filtering and prove probably approximately correct (PAC)-style guarantees: if the set approximation error is bounded by <span><math><mi>ɛ</mi></math></span> with confidence <span><math><mrow><mn>1</mn><mo>−</mo><mi>δ</mi></mrow></math></span>, then the probability of constraint violation along a length–<span><math><mi>T</mi></math></span> rollout is bounded by a term that scales linearly in <span><math><mi>T</mi></math></span> and <span><math><mi>ɛ</mi></math></span> (plus <span><math><mi>δ</mi></math></span>). We further show that the performance suboptimality of the filtered policy is controlled analytically by the same approximation envelope, yielding an explicit, provably quantified safety-versus-optimality tradeoff (PAC bounds linear in <span><math><mi>T</mi></math></span> and the envelope), complemented by empirical ablations; see also the calculus-of-variations view of constrained tradeoffs (Younis, 2023). The resulting method, <strong>CTR-Net</strong>, is architecture-agnostic and supports real-time execution via fast, differentiable safety layers. Empirical evaluations on high-dimensional continuous-control benchmarks — including safe locomotion and constrained multi-joint manipulation — demonstrate reliable constraint satisfaction during learning and deployment, robustness under modeling uncertainty and substantial computational gains relative to exact viability/barrier baselines. By coupling operator-free neural safety sets with CTR guarantees, CTR-Net bridges theoretical safety certificates and scalable implementation, advancing practical, real-time safe RL for complex intelligent systems.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200597"},"PeriodicalIF":4.3,"publicationDate":"2025-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145416658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-31DOI: 10.1016/j.iswa.2025.200600
Mohamad Al Assaad, Stéphane Bazeille, Christophe Cudel
Visual odometry is the technique of determining a robot’s pose by analyzing images of its surroundings as it moves. Visual odometry can be categorized into monocular when using a single camera, or stereo when using two cameras or more. In this study, we investigate the use of light-field camera for visual odometry. Capitalizing on the distinctive capability of a light-field camera to record both the intensity and the direction of light, we propose an indirect visual odometry method able to estimate the scale of the translation similarly to stereo visual odometry, but using a single camera sensor. Our visual odometry framework combines light-field imaging with conventional odometry techniques to track the camera movements, using the depth insights provided by a light-field depth estimation approach. Additionally, this method differs from state-of-the-art methods by using a simplified calibration process and a new keypoints extraction method, which makes the use of the light-field cameras easier for robotics perception.
{"title":"Indirect visual odometry with a light-field camera","authors":"Mohamad Al Assaad, Stéphane Bazeille, Christophe Cudel","doi":"10.1016/j.iswa.2025.200600","DOIUrl":"10.1016/j.iswa.2025.200600","url":null,"abstract":"<div><div>Visual odometry is the technique of determining a robot’s pose by analyzing images of its surroundings as it moves. Visual odometry can be categorized into monocular when using a single camera, or stereo when using two cameras or more. In this study, we investigate the use of light-field camera for visual odometry. Capitalizing on the distinctive capability of a light-field camera to record both the intensity and the direction of light, we propose an indirect visual odometry method able to estimate the scale of the translation similarly to stereo visual odometry, but using a single camera sensor. Our visual odometry framework combines light-field imaging with conventional odometry techniques to track the camera movements, using the depth insights provided by a light-field depth estimation approach. Additionally, this method differs from state-of-the-art methods by using a simplified calibration process and a new keypoints extraction method, which makes the use of the light-field cameras easier for robotics perception.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"28 ","pages":"Article 200600"},"PeriodicalIF":4.3,"publicationDate":"2025-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号