Pub Date : 2026-01-21DOI: 10.1016/j.fraope.2026.100511
Marzia Ahmed , Mohd Herwan Sulaiman , Md Shofiqul Islam , Shahrin Islam
SARS-CoV-2 is a multi-organ disease with a broad range of symptoms. Extensive research has been conducted to improve early detection, syndrome prediction, and diagnosis. However, the persistent condition experienced by recovered patients with COVID-19, known as post-acute sequelae of COVID-19 (PASC), remains underexplored. This review aims to analyze PASC symptoms, assess their risk intensity based on medical history, and highlight emerging variants. Unlike existing reviews, this article uniquely integrates machine learning techniques for personalized assessment of PASC risk and mapping of symptoms through an interactive platform. It introduces a conceptual framework that utilizes real-time patient data, enabling more accurate predictions and multidisciplinary treatment recommendations. The framework allows long-COVID patients to input symptoms via an app or website, which are then mapped against PASC datasets to assign risk levels (low, medium, or high). Machine learning models process these data for feature engineering and classification to predict the persistence of PASC. By leveraging machine learning for real-time risk stratification and treatment suggestions, this study advances post-COVID care beyond traditional symptom tracking. The proposed methodology is expected to outperform existing systems in predictive accuracy and patient-specific recommendations.
{"title":"Machine learning for early detection of post-acute sequelae of COVID-19 (PASC): A comparative review of symptoms and risk factors","authors":"Marzia Ahmed , Mohd Herwan Sulaiman , Md Shofiqul Islam , Shahrin Islam","doi":"10.1016/j.fraope.2026.100511","DOIUrl":"10.1016/j.fraope.2026.100511","url":null,"abstract":"<div><div>SARS-CoV-2 is a multi-organ disease with a broad range of symptoms. Extensive research has been conducted to improve early detection, syndrome prediction, and diagnosis. However, the persistent condition experienced by recovered patients with COVID-19, known as post-acute sequelae of COVID-19 (PASC), remains underexplored. This review aims to analyze PASC symptoms, assess their risk intensity based on medical history, and highlight emerging variants. Unlike existing reviews, this article uniquely integrates machine learning techniques for personalized assessment of PASC risk and mapping of symptoms through an interactive platform. It introduces a conceptual framework that utilizes real-time patient data, enabling more accurate predictions and multidisciplinary treatment recommendations. The framework allows long-COVID patients to input symptoms via an app or website, which are then mapped against PASC datasets to assign risk levels (low, medium, or high). Machine learning models process these data for feature engineering and classification to predict the persistence of PASC. By leveraging machine learning for real-time risk stratification and treatment suggestions, this study advances post-COVID care beyond traditional symptom tracking. The proposed methodology is expected to outperform existing systems in predictive accuracy and patient-specific recommendations.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100511"},"PeriodicalIF":0.0,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037821","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 : 2026-01-21DOI: 10.1016/j.fraope.2026.100509
Md. Rafiqul Islam , Mehedy Hasan , Rajib Biswas , B.M. Jewel Rana , Sarder Firoz Ahmmed , Shekh Nisar Hossain , Mohammad Afikuzzaman
This study presents a detailed investigation of the two-dimensional magnetohydrodynamic (MHD) flow of a Casson hybrid nanofluid with chemical reactions through a perpendicular porous channel under sinusoidal boundary conditions. The introduction of periodic MHD effects and oscillatory wall motion represents the key novelty of this work. The governing nonlinear partial differential equations are transformed into non-dimensional form and solved using a hybrid analytical–numerical approach, with stability and convergence analyses confirming the reliability of the solution. Flow and heat transfer characteristics are analyzed through streamline and isotherm visualizations. The results reveal that the Grashof number and heat source parameter enhance skin friction, while higher Prandtl number, magnetic parameter, porosity, and chemical reaction rate suppress it. Notably, a 25% reduction in velocity is observed as the magnetic parameter increases from 1 to 5, with similar trends evident for other parameters. The findings exhibit strong agreement with existing studies and highlight the model’s practical relevance to biomedical fluid transport, thermal management in electronic systems, and various industrial and manufacturing applications.
{"title":"Mathematical modelling of periodic MHD Casson fluid flow for sinusoidal boundary conditions in terms of chemical responses and thermal radiation","authors":"Md. Rafiqul Islam , Mehedy Hasan , Rajib Biswas , B.M. Jewel Rana , Sarder Firoz Ahmmed , Shekh Nisar Hossain , Mohammad Afikuzzaman","doi":"10.1016/j.fraope.2026.100509","DOIUrl":"10.1016/j.fraope.2026.100509","url":null,"abstract":"<div><div>This study presents a detailed investigation of the two-dimensional magnetohydrodynamic (MHD) flow of a Casson hybrid nanofluid with chemical reactions through a perpendicular porous channel under sinusoidal boundary conditions. The introduction of periodic MHD effects and oscillatory wall motion represents the key novelty of this work. The governing nonlinear partial differential equations are transformed into non-dimensional form and solved using a hybrid analytical–numerical approach, with stability and convergence analyses confirming the reliability of the solution. Flow and heat transfer characteristics are analyzed through streamline and isotherm visualizations. The results reveal that the Grashof number and heat source parameter enhance skin friction, while higher Prandtl number, magnetic parameter, porosity, and chemical reaction rate suppress it. Notably, a 25% reduction in velocity is observed as the magnetic parameter increases from 1 to 5, with similar trends evident for other parameters. The findings exhibit strong agreement with existing studies and highlight the model’s practical relevance to biomedical fluid transport, thermal management in electronic systems, and various industrial and manufacturing applications.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100509"},"PeriodicalIF":0.0,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146090636","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 : 2026-01-16DOI: 10.1016/j.fraope.2026.100487
Li Li , Shunqin Liu , Xiuliang Qiu , Wenshui Lin
This study investigates exponential synchronization for complex networks with nonlinear coupling structures, stochastic perturbations, and hybrid time-varying delays. The proposed model integrates both internal and coupling-induced time-varying delays. A pinning impulsive control strategy is developed to synchronize the network, which only requires partial node intervention. Based on stochastic analysis and Lyapunov stability theory, we rigorously derive sufficient conditions for exponential convergence. The results reveal that synchronizing the entire network requires only limited impulsive control inputs, significantly reducing control costs. Finally, two numerical examples validate the theoretical framework and demonstrate its practical effectiveness.
{"title":"Achieving exponential synchronization in nonlinear stochastic complex networks with time-varying delays: A pinning impulsive control strategy","authors":"Li Li , Shunqin Liu , Xiuliang Qiu , Wenshui Lin","doi":"10.1016/j.fraope.2026.100487","DOIUrl":"10.1016/j.fraope.2026.100487","url":null,"abstract":"<div><div>This study investigates exponential synchronization for complex networks with nonlinear coupling structures, stochastic perturbations, and hybrid time-varying delays. The proposed model integrates both internal and coupling-induced time-varying delays. A pinning impulsive control strategy is developed to synchronize the network, which only requires partial node intervention. Based on stochastic analysis and Lyapunov stability theory, we rigorously derive sufficient conditions for exponential convergence. The results reveal that synchronizing the entire network requires only limited impulsive control inputs, significantly reducing control costs. Finally, two numerical examples validate the theoretical framework and demonstrate its practical effectiveness.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100487"},"PeriodicalIF":0.0,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037822","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 : 2026-01-15DOI: 10.1016/j.fraope.2026.100501
Farida Siddiqi Prity , Mirza Raquib , Abdullah Al Shiam , Md. Maruf Hossain , K.M. Aslam Uddin
Rice diseases significantly reduce crop productivity and pose a serious threat to global food security. Early and accurate identification of rice leaf diseases is therefore essential to enable timely intervention and effective disease management. Recent studies have applied Artificial Neural Networks (ANNs) with single feature extraction or direct imaging methods; however, these approaches often suffer from limited feature representation, poor generalization, high computational cost, and limited interpretability. Moreover, the comparative effectiveness of hybrid feature extraction strategies remains insufficiently explored. To address these challenges, this study proposes a novel hybrid feature extraction algorithm, GreyTexFWave, which integrates Gray Level Co-occurrence Matrix (GLCM), Gray Level Dependence Matrix (GLDM), Texture, Fast Fourier Transform (FFT), and Discrete Wavelet Transform (DWT) features to capture both spatial and frequency-domain characteristics of rice leaf images. The extracted features are classified using a Feed-Forward Neural Network (FFNN). Experiments were conducted on a balanced dataset containing images of bacterial leaf blight, stemborer, and tungro diseases. Model performance was evaluated using accuracy, sensitivity, precision, and F-measure, and compared against individual feature extraction methods. The proposed GreyTexFWave-based FFNN achieved an average accuracy of 94.84 ± 0.04%, with 94.9% sensitivity, 88.7% precision, and 91.7% F-measure, outperforming all single-feature extraction approaches. A paired t-test further confirmed that the performance improvements are statistically significant. The results demonstrate that hybrid feature extraction substantially enhances rice disease classification performance. The proposed approach offers a practical and interpretable solution for early rice disease detection, supporting precision agriculture and reducing yield losses through timely disease management.
{"title":"Rice disease classification using feed-forward neural network: Comparative analysis between hybrid and single feature extraction algorithms","authors":"Farida Siddiqi Prity , Mirza Raquib , Abdullah Al Shiam , Md. Maruf Hossain , K.M. Aslam Uddin","doi":"10.1016/j.fraope.2026.100501","DOIUrl":"10.1016/j.fraope.2026.100501","url":null,"abstract":"<div><div>Rice diseases significantly reduce crop productivity and pose a serious threat to global food security. Early and accurate identification of rice leaf diseases is therefore essential to enable timely intervention and effective disease management. Recent studies have applied Artificial Neural Networks (ANNs) with single feature extraction or direct imaging methods; however, these approaches often suffer from limited feature representation, poor generalization, high computational cost, and limited interpretability. Moreover, the comparative effectiveness of hybrid feature extraction strategies remains insufficiently explored. To address these challenges, this study proposes a novel hybrid feature extraction algorithm, GreyTexFWave, which integrates Gray Level Co-occurrence Matrix (GLCM), Gray Level Dependence Matrix (GLDM), Texture, Fast Fourier Transform (FFT), and Discrete Wavelet Transform (DWT) features to capture both spatial and frequency-domain characteristics of rice leaf images. The extracted features are classified using a Feed-Forward Neural Network (FFNN). Experiments were conducted on a balanced dataset containing images of bacterial leaf blight, stemborer, and tungro diseases. Model performance was evaluated using accuracy, sensitivity, precision, and F-measure, and compared against individual feature extraction methods. The proposed GreyTexFWave-based FFNN achieved an average accuracy of 94.84 ± 0.04%, with 94.9% sensitivity, 88.7% precision, and 91.7% F-measure, outperforming all single-feature extraction approaches. A paired <em>t</em>-test further confirmed that the performance improvements are statistically significant. The results demonstrate that hybrid feature extraction substantially enhances rice disease classification performance. The proposed approach offers a practical and interpretable solution for early rice disease detection, supporting precision agriculture and reducing yield losses through timely disease management.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100501"},"PeriodicalIF":0.0,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023113","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 : 2026-01-15DOI: 10.1016/j.fraope.2026.100508
K.A. Rybakov, E.D. Shermatov
This paper proposes a new technique for computer modeling linear filters based on the spectral form of mathematical description of linear systems. It assumes the representation of input and output signals of the filter as orthogonal expansions, while filters themselves are described by two-dimensional non-stationary transfer functions. This technique allows one to model the output signal in continuous time, and it is successfully tested on the Butterworth, Linkwitz–Riley, and Chebyshev filters with different orders.
{"title":"Applying the spectral method for modeling linear filters: Butterworth, Linkwitz–Riley, and Chebyshev filters","authors":"K.A. Rybakov, E.D. Shermatov","doi":"10.1016/j.fraope.2026.100508","DOIUrl":"10.1016/j.fraope.2026.100508","url":null,"abstract":"<div><div>This paper proposes a new technique for computer modeling linear filters based on the spectral form of mathematical description of linear systems. It assumes the representation of input and output signals of the filter as orthogonal expansions, while filters themselves are described by two-dimensional non-stationary transfer functions. This technique allows one to model the output signal in continuous time, and it is successfully tested on the Butterworth, Linkwitz–Riley, and Chebyshev filters with different orders.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100508"},"PeriodicalIF":0.0,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146090707","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}
Medical image processing is an essential challenge in a wide range of applications in today’s clinical scenario. Such applications can be served throughout the clinical course of events, not just in the diagnostic environment but also in the planning, execution, and progression of surgical and radiation procedures. The role of medical imaging information retrieval and processing is significant in surgical planning and tracking the progress of diseases. So, using state of the art computing techniques, researchers have made efforts to propose an effective automated technique to determine Diabetic Retinopathy (DR) based on significant medical image features and the patient’s clinical history. In this work, an intelligent graph-based methodology is proposed, considering the concepts from Rough Set Theory for feature selection. Based on several centrality metrics of graphs, a voting method is proposed to identify important features, resulting in better classification outcomes for diabetic retinopathy. Proposed methods are compared with several existing baseline feature selection approaches and provide better feature selection outcomes than those existing approaches. The result shows significantly better classification outcomes with respect to classical classification approaches.
{"title":"Rough set based feature selection model for diabetic retinopathy classification","authors":"Abhishek Bhattacharya, Blerta Prevalla Etemi, Debabrata Samanta","doi":"10.1016/j.fraope.2026.100491","DOIUrl":"10.1016/j.fraope.2026.100491","url":null,"abstract":"<div><div>Medical image processing is an essential challenge in a wide range of applications in today’s clinical scenario. Such applications can be served throughout the clinical course of events, not just in the diagnostic environment but also in the planning, execution, and progression of surgical and radiation procedures. The role of medical imaging information retrieval and processing is significant in surgical planning and tracking the progress of diseases. So, using state of the art computing techniques, researchers have made efforts to propose an effective automated technique to determine Diabetic Retinopathy (DR) based on significant medical image features and the patient’s clinical history. In this work, an intelligent graph-based methodology is proposed, considering the concepts from Rough Set Theory for feature selection. Based on several centrality metrics of graphs, a voting method is proposed to identify important features, resulting in better classification outcomes for diabetic retinopathy. Proposed methods are compared with several existing baseline feature selection approaches and provide better feature selection outcomes than those existing approaches. The result shows significantly better classification outcomes with respect to classical classification approaches.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100491"},"PeriodicalIF":0.0,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977463","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 : 2026-01-14DOI: 10.1016/j.fraope.2026.100500
Akintayo Emmanuel Akinsunmade , Ahmed Oluseun Afolabi
Human African Trypanosomiasis (HAT) remains a persistent public health challenge due to its complex zoonotic transmission cycle and high endemic potential. This study introduces a mathematical model that explicitly integrates stage-specific human clinical progression with a dynamic cattle reservoir and mechanistic vector control to evaluate intervention strategies within a One Health framework. Comprehensive analysis using the normalized forward sensitivity index and Latin Hypercube Sampling-Partial Rank Correlation Coefficient (LHS-PRCC) identifies the cattle cycle as the dominant transmission pathway, contributing approximately 97.8% of the overall epidemic risk. Notably, cattle treatment was identified as the most influential single lever for reducing the basic reproduction number, while the tsetse biting rate and mortality remain the primary environmental drivers of infection. Numerical simulations validate these theoretical findings, demonstrating that single interventions are insufficient for sustained elimination. While human treatment provides essential clinical benefits by rapidly reducing morbidity, its impact on the population-level epidemic threshold is negligible. Conversely, integrated cattle treatment and vector control are highly effective at clearing the primary animal reservoir and infectious vector pools. The model decisively demonstrates that only a combined strategy, leveraging animal reservoir clearance alongside immediate clinical care, can successfully drive disease prevalence to a near-zero state. Consequently, this study recommends a policy shift from human-centric care to an integrated host-vector management framework. Prioritizing interventions at the cattle-vector interface is essential to meet the World Health Organization (WHO) 2030 targets and achieve sustainable local elimination.
{"title":"Mathematical model for trypanosomiasis management integrating treatment enhancement, vector control, and host management strategies","authors":"Akintayo Emmanuel Akinsunmade , Ahmed Oluseun Afolabi","doi":"10.1016/j.fraope.2026.100500","DOIUrl":"10.1016/j.fraope.2026.100500","url":null,"abstract":"<div><div>Human African Trypanosomiasis (HAT) remains a persistent public health challenge due to its complex zoonotic transmission cycle and high endemic potential. This study introduces a mathematical model that explicitly integrates stage-specific human clinical progression with a dynamic cattle reservoir and mechanistic vector control to evaluate intervention strategies within a One Health framework. Comprehensive analysis using the normalized forward sensitivity index and Latin Hypercube Sampling-Partial Rank Correlation Coefficient (LHS-PRCC) identifies the cattle cycle as the dominant transmission pathway, contributing approximately 97.8% of the overall epidemic risk. Notably, cattle treatment was identified as the most influential single lever for reducing the basic reproduction number, while the tsetse biting rate and mortality remain the primary environmental drivers of infection. Numerical simulations validate these theoretical findings, demonstrating that single interventions are insufficient for sustained elimination. While human treatment provides essential clinical benefits by rapidly reducing morbidity, its impact on the population-level epidemic threshold is negligible. Conversely, integrated cattle treatment and vector control are highly effective at clearing the primary animal reservoir and infectious vector pools. The model decisively demonstrates that only a combined strategy, leveraging animal reservoir clearance alongside immediate clinical care, can successfully drive disease prevalence to a near-zero state. Consequently, this study recommends a policy shift from human-centric care to an integrated host-vector management framework. Prioritizing interventions at the cattle-vector interface is essential to meet the World Health Organization (WHO) 2030 targets and achieve sustainable local elimination.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100500"},"PeriodicalIF":0.0,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977462","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 : 2026-01-14DOI: 10.1016/j.fraope.2026.100497
Mohamed Ali Farag , Mohamed H. Khafagy , Shereen A. Hussien
The exponential growth of digital video content has intensified the demand for automated video captioning systems that can bridge visual understanding and natural language processing. Video captioning, which generates descriptive sentences for video sequences, plays a crucial role in enhancing accessibility, content retrieval, and human–computer interaction. This paper presents a novel Video Captioning using Deep Learning with Greedy Search (VCDLGS) model that addresses the challenges of temporal dynamics and contextual dependencies inherent in video content. The proposed framework integrates EfficientNet for robust visual feature extraction, GloVe semantic embeddings for enhanced linguistic representation, and a sequence-to-sequence Long Short-Term Memory architecture with multimodal attention mechanisms. The model employs a greedy search decoding strategy to generate coherent and contextually relevant captions efficiently. Comprehensive evaluation on the Microsoft Research Video Description Corpus dataset demonstrates the effectiveness of our approach, achieving competitive performance with a BLEU score of 64.82 (23.12 point improvement over S2VT baseline), METEOR score of 46.10 (16.90 point improvement), and CIDEr score of 144.00 (92.30 point improvement). These results represent substantial advances over several state-of-the-art baselines, with greedy search providing 42% faster inference than beam search while maintaining comparable quality. The VCDLGS model contributes to advancing automated video understanding technology while providing an efficient solution suitable for real-time applications with 18.5 fps processing capability. This work establishes a foundation for improved content accessibility and multimedia comprehension across diverse domains.
{"title":"Video Captioning using Deep Learning with Greedy Search (VCDLGS)","authors":"Mohamed Ali Farag , Mohamed H. Khafagy , Shereen A. Hussien","doi":"10.1016/j.fraope.2026.100497","DOIUrl":"10.1016/j.fraope.2026.100497","url":null,"abstract":"<div><div>The exponential growth of digital video content has intensified the demand for automated video captioning systems that can bridge visual understanding and natural language processing. Video captioning, which generates descriptive sentences for video sequences, plays a crucial role in enhancing accessibility, content retrieval, and human–computer interaction. This paper presents a novel Video Captioning using Deep Learning with Greedy Search (VCDLGS) model that addresses the challenges of temporal dynamics and contextual dependencies inherent in video content. The proposed framework integrates EfficientNet for robust visual feature extraction, GloVe semantic embeddings for enhanced linguistic representation, and a sequence-to-sequence Long Short-Term Memory architecture with multimodal attention mechanisms. The model employs a greedy search decoding strategy to generate coherent and contextually relevant captions efficiently. Comprehensive evaluation on the Microsoft Research Video Description Corpus dataset demonstrates the effectiveness of our approach, achieving competitive performance with a BLEU score of 64.82 (23.12 point improvement over S2VT baseline), METEOR score of 46.10 (16.90 point improvement), and CIDEr score of 144.00 (92.30 point improvement). These results represent substantial advances over several state-of-the-art baselines, with greedy search providing 42% faster inference than beam search while maintaining comparable quality. The VCDLGS model contributes to advancing automated video understanding technology while providing an efficient solution suitable for real-time applications with 18.5 fps processing capability. This work establishes a foundation for improved content accessibility and multimedia comprehension across diverse domains.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100497"},"PeriodicalIF":0.0,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037820","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 : 2026-01-14DOI: 10.1016/j.fraope.2026.100486
Zhaoqi Liu, Juan Chen, Yu Liu, Lilan Tu
Prescribed-time synchronization in complex networks has garnered significant research attention due to its broad engineering applications. While existing synchronization studies predominantly consider scalar-weighted node interactions, real-world network systems frequently require matrix-weighted representations to accurately capture multidimensional state coupling between nodes. This paper systematically investigates prescribed-time synchronization in matrix-weighted complex networks with both undirected and directed topologies. By constructing a Lyapunov-based analytical framework, we establish rigorous synchronization conditions that guarantee convergence within the prescribed time horizon. Extensive numerical simulations not only validate the theoretical results but also demonstrate the method’s versatility across diverse network configurations. The proposed approach provides a unified control framework with potential applications in power grid synchronization, neural network coordination, and social network dynamics, offering substantial improvements over conventional scalar-weighted network models.
{"title":"Prescribed-time synchronization of undirected and directed matrix-weighted networks","authors":"Zhaoqi Liu, Juan Chen, Yu Liu, Lilan Tu","doi":"10.1016/j.fraope.2026.100486","DOIUrl":"10.1016/j.fraope.2026.100486","url":null,"abstract":"<div><div>Prescribed-time synchronization in complex networks has garnered significant research attention due to its broad engineering applications. While existing synchronization studies predominantly consider scalar-weighted node interactions, real-world network systems frequently require matrix-weighted representations to accurately capture multidimensional state coupling between nodes. This paper systematically investigates prescribed-time synchronization in matrix-weighted complex networks with both undirected and directed topologies. By constructing a Lyapunov-based analytical framework, we establish rigorous synchronization conditions that guarantee convergence within the prescribed time horizon. Extensive numerical simulations not only validate the theoretical results but also demonstrate the method’s versatility across diverse network configurations. The proposed approach provides a unified control framework with potential applications in power grid synchronization, neural network coordination, and social network dynamics, offering substantial improvements over conventional scalar-weighted network models.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100486"},"PeriodicalIF":0.0,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977466","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}
Mobile communication security is increasingly threatened by smishing messages, necessitating advanced detection techniques to protect users from fraudulent and malicious content. This paper presents a hybrid approach that combines Term Frequency–Inverse Document Frequency (TF-IDF) with fuzzy membership–based linguistic and structural features to enhance smishing messages classification. The feature extraction process includes word count, punctuation usage, message length, sentiment polarity, capitalization patterns, and digit frequency. Fuzzy membership functions encode these attributes as gradual values rather than fixed thresholds, improving adaptability to evolving smishing patterns. These fuzzy features are concatenated with TF-IDF vectors to form a comprehensive representation that captures both semantic and stylistic characteristics. The proposed framework is evaluated on a dataset of 6119 SMS messages, comprising 5574 messages from the SMS Spam Collection v.1 and an additional 545 smishing messages from the Smishtank repository. Experimental results demonstrate that the proposed model achieves up to 99.10% accuracy, 99.30% precision, and 94% recall, outperforming existing methods such as SVM (97.40%) and Random Forest (98.15%). Furthermore, the incorporation of fuzzy membership concepts enhances adaptability to diverse smishing patterns, reduces false alarms, and improves the overall robustness of the classification framework.
{"title":"Machine learning-based smishing detection using fuzzy logic and TF-IDF feature engineering","authors":"Santosh Kumar Birthriya, Priyanka Ahlawat, Ankit Kumar Jain","doi":"10.1016/j.fraope.2026.100506","DOIUrl":"10.1016/j.fraope.2026.100506","url":null,"abstract":"<div><div>Mobile communication security is increasingly threatened by smishing messages, necessitating advanced detection techniques to protect users from fraudulent and malicious content. This paper presents a hybrid approach that combines Term Frequency–Inverse Document Frequency (TF-IDF) with fuzzy membership–based linguistic and structural features to enhance smishing messages classification. The feature extraction process includes word count, punctuation usage, message length, sentiment polarity, capitalization patterns, and digit frequency. Fuzzy membership functions encode these attributes as gradual values rather than fixed thresholds, improving adaptability to evolving smishing patterns. These fuzzy features are concatenated with TF-IDF vectors to form a comprehensive representation that captures both semantic and stylistic characteristics. The proposed framework is evaluated on a dataset of 6119 SMS messages, comprising 5574 messages from the SMS Spam Collection v.1 and an additional 545 smishing messages from the Smishtank repository. Experimental results demonstrate that the proposed model achieves up to 99.10% accuracy, 99.30% precision, and 94% recall, outperforming existing methods such as SVM (97.40%) and Random Forest (98.15%). Furthermore, the incorporation of fuzzy membership concepts enhances adaptability to diverse smishing patterns, reduces false alarms, and improves the overall robustness of the classification framework.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100506"},"PeriodicalIF":0.0,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146090637","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