Franklin Open最新文献_第2页

Bayesian prediction of under-five mortality rates for Tanzania

Franklin Open Pub Date : 2025-01-26 DOI: 10.1016/j.fraope.2025.100221

Mohamed K. Mwanga , Silas S. Mirau , Jean M. Tchuenche , Isambi S. Mbalawata

引用次数: 0

Energy equivalent consumption and optimization strategies for hybrid hydrogen fuel systems in multirotor drones

Franklin Open Pub Date : 2025-01-23 DOI: 10.1016/j.fraope.2025.100211

Xiangyu Zhang , Yong Zhang , Xin Wang , Tingting Ru , Chenxiao Cai

{"title":"Energy equivalent consumption and optimization strategies for hybrid hydrogen fuel systems in multirotor drones","authors":"Xiangyu Zhang , Yong Zhang , Xin Wang , Tingting Ru , Chenxiao Cai","doi":"10.1016/j.fraope.2025.100211","DOIUrl":"10.1016/j.fraope.2025.100211","url":null,"abstract":"<div><div>This paper presents an improved Equivalent Consumption Minimization Strategy (ECMS) designed to optimize energy management for the hybrid hydrogen fuel power setups in multirotor drones. The proposed strategy aims to reduce hydrogen consumption and enhance the performance of the system consisting of Proton Exchange Membrane Fuel Cells (PEMFCs) and lithium batteries. Multirotor drones experience rapid power fluctuations due to their agile maneuvering, but PEMFCs are unable to meet these demands swiftly due to their inherent limitations. To address this, lithium batteries supplement peak power requirements and absorb excess energy on the DC bus. However, this can lead to energy loss if the batteries are charged when not required. Our improved ECMS considers these inefficiencies and adjusts energy distribution to reduce hydrogen consumption and optimize the system’s performance. The proposed strategy effectively maintains the lithium batteries’ State of Charge (SOC), reduces hydrogen usage and enhances overall system efficiency when compared to traditional ECMS approaches.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"10 ","pages":"Article 100211"},"PeriodicalIF":0.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach

Franklin Open Pub Date : 2025-01-22 DOI: 10.1016/j.fraope.2025.100222

Raquel Ochoa-Ornelas , Alberto Gudiño-Ochoa , Julio Alberto García-Rodríguez , Sofia Uribe-Toscano

{"title":"Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach","authors":"Raquel Ochoa-Ornelas , Alberto Gudiño-Ochoa , Julio Alberto García-Rodríguez , Sofia Uribe-Toscano","doi":"10.1016/j.fraope.2025.100222","DOIUrl":"10.1016/j.fraope.2025.100222","url":null,"abstract":"<div><div>Lung cancer is the leading cause of cancer-related mortality globally, with over 2.2 million new cases diagnosed annually. Early detection is critical for improving patient outcomes but remains a significant challenge due to the intricate nature of histopathological image analysis, which requires specialized expertise. This study investigates the application of MobileNetV2, a state-of-the-art, lightweight convolutional neural network, for the accurate classification of lung adenocarcinoma (LAC), benign lung tissue (BLT), and lung squamous cell carcinoma (LUSC). To enhance the model’s generalization capabilities, we augmented the widely used LC25000 dataset with additional histopathological images sourced from the National Cancer Institute. The final model exhibited exceptional performance, achieving a training accuracy of 99.11%, a validation accuracy of 97.25%, and a test accuracy of 97.65%. The model also delivered high precision, recall, and F1-scores, each exceeding 98% across all classes, with perfect metrics observed for BLT. These promising results highlight the potential of MobileNetV2 as a highly effective tool for the early detection of lung cancer, offering substantial support for clinical diagnosis. By facilitating more accurate and timely diagnoses, this approach has the potential to significantly enhance patient care and improve survival rates in lung cancer patients.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"10 ","pages":"Article 100222"},"PeriodicalIF":0.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review of quantum communication and information networks with advanced cryptographic applications using machine learning, deep learning techniques

Franklin Open Pub Date : 2025-01-22 DOI: 10.1016/j.fraope.2025.100223

R. Ramya, P. Kumar, D. Dhanasekaran, R. Satheesh Kumar, S. Amithesh Sharavan

{"title":"A review of quantum communication and information networks with advanced cryptographic applications using machine learning, deep learning techniques","authors":"R. Ramya, P. Kumar, D. Dhanasekaran, R. Satheesh Kumar, S. Amithesh Sharavan","doi":"10.1016/j.fraope.2025.100223","DOIUrl":"10.1016/j.fraope.2025.100223","url":null,"abstract":"<div><div>Quantum communication and information networks offer unprecedented processing efficiency and security for data transfers. Technologies like quantum key distribution (QKD), quantum repeaters, quantum memory, and quantum entanglement sources are enabling technologies that ensure secure communication. QKD methods use quantum physics concepts to establish cryptographic keys, while quantum repeaters compensate for signal loss in fiber optic cables. Quantum memory enables storage and retrieval of quantum information, while quantum entanglement generators generate entangled photon pairs. Artificial intelligence and machine learning have significantly improved the efficacy and security of quantum communication. These methods can facilitate ultra-secure, reliable, large-scale communication and even a future quantum internet by analyzing quantum protocols and mitigating noise-induced errors. QKD protocols ensure secure communication channels, while quantum repeaters establish secure long-distance communication lines by mitigating signal loss. Traditional Internet technology is susceptible to surveillance due to Shannon's information theory and mathematics. The quantum internet (QI) uses satellite-based quantum communication and quantum cryptographic protocols for physical QI. Quantum entanglement sources fortify secure communication protocols, improving resistance to attacks. Quantum information networks (QINs) enhance computing, sensing, and security capabilities over extended distances. The development of reliable, robust communication systems depends on these technologies. Quantum-secured networks enhance urban security, smart management, and infrastructure protection by providing data privacy and facilitating secure data transmission, thereby facilitating robust infrastructure and technological development.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"10 ","pages":"Article 100223"},"PeriodicalIF":0.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mamba vision models: Automated American sign language recognition

Franklin Open Pub Date : 2025-01-22 DOI: 10.1016/j.fraope.2025.100224

Ali Salem Altaher , Chiron Bang , Bader Alsharif , Ahmed Altaher , Munid Alanazi , Hasan Altaher , Hanqi Zhuang

{"title":"Mamba vision models: Automated American sign language recognition","authors":"Ali Salem Altaher , Chiron Bang , Bader Alsharif , Ahmed Altaher , Munid Alanazi , Hasan Altaher , Hanqi Zhuang","doi":"10.1016/j.fraope.2025.100224","DOIUrl":"10.1016/j.fraope.2025.100224","url":null,"abstract":"<div><div>Historically, individuals with hearing impairments have faced significant challenges in effective communication due to the lack of adequate resources. Recent technological advancements have spurred the development of innovative tools aimed at enhancing the quality of life for those with hearing disabilities. This research focuses on the application of Vision Mamba Models for classifying hand gestures representing the American Sign Language (ASL) alphabet, with a detailed comparative analysis of its performance against 13 deep learning architectures. The Vision Mamba Models, namely, Vision Mamba and Remote Sensing Mamba, were trained on a substantial dataset comprising 87,000 images of ASL hand gestures, and through iterative fine-tuning of their architectural parameters, the models’ accuracy and performance were optimized. Experimental results demonstrated that the Mamba Vision Models outperformed all other models previously examined in this context scoring exceptional accuracy rate that exceeded 99.98%, with less architectural complexity. These findings highlight the potential of deep learning technologies, particularly the Mamba vision models, in advancing assistive technologies, offering a sophisticated and highly accurate tool for interpreting ASL hand gestures and promising improved communication and accessibility for individuals with hearing impairments.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"10 ","pages":"Article 100224"},"PeriodicalIF":0.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improved coordinate attention network for classification of dangerous driving behavior

Franklin Open Pub Date : 2025-01-21 DOI: 10.1016/j.fraope.2025.100219

Wen Ni , Lufeng Bai

{"title":"Improved coordinate attention network for classification of dangerous driving behavior","authors":"Wen Ni , Lufeng Bai","doi":"10.1016/j.fraope.2025.100219","DOIUrl":"10.1016/j.fraope.2025.100219","url":null,"abstract":"<div><div>With the rise of traffic accidents caused by unsafe driving behaviors, the accurate classification of these behaviors has become a pressing issue in intelligent transportation systems. Traditional methods such as AlexNet and VGG, while effective for general image recognition tasks, fail to capture the complex and subtle features necessary for recognizing dangerous driving behaviors. To address this, we propose an improved residual network model, SC-ResNet, which integrates a coordinate attention mechanism and SIFT (Scale-Invariant Feature Transform) feature fusion to enhance classification accuracy under varying conditions including rotation, scale, and illumination changes. Furthermore, we introduce a multi-scale feature pyramid network and a novel joint loss function to better handle the multi-class classification imbalance problem. Experimental results show that our model outperforms traditional networks by <span><math><mrow><mn>0</mn><mo>.</mo><mn>6</mn><mtext>%</mtext></mrow></math></span> to <span><math><mrow><mn>4</mn><mo>.</mo><mn>7</mn><mtext>%</mtext></mrow></math></span> in classification accuracy. Future research will focus on improving model generalization and computational efficiency for real-time applications.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"10 ","pages":"Article 100219"},"PeriodicalIF":0.0,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Refining instantaneous frequency estimation: Tackling abrupt transitions in aliased non-stationary signals

Franklin Open Pub Date : 2025-01-21 DOI: 10.1016/j.fraope.2025.100217

Sadiq Ali , Nabeel Ali Khan

引用次数: 0

A mathematical model of corruption dynamics and optimal control

Franklin Open Pub Date : 2025-01-18 DOI: 10.1016/j.fraope.2025.100216

Mostak Ahmed, Mostofa Kamal, M. Alamgir Hossain

引用次数: 0

Numerical simulation and dynamical system for solving biomathematical model with optimal control

Franklin Open Pub Date : 2025-01-16 DOI: 10.1016/j.fraope.2025.100218

A.M.S. Mahdy , D.S. Mohamed

{"title":"Numerical simulation and dynamical system for solving biomathematical model with optimal control","authors":"A.M.S. Mahdy , D.S. Mohamed","doi":"10.1016/j.fraope.2025.100218","DOIUrl":"10.1016/j.fraope.2025.100218","url":null,"abstract":"<div><div>This study shows that have understand SEIASqEqHR models work dynamically and we have depended on the Legendre-Galerkin procedure to explain that. We have displayed the creation of a brand new flow chart that displays the coronavirus form. The SEIASqEqHR form is based on the Legendre-Galerkin method. The proposed number-based ways of doing things are fantastic. Our statistical analysis has revealed that social isolation between potentially infected carriers of the illness and healthy people may be able to stop or slow the illness from spreading. The outcomes are expressed mathematically and emotionally detached from the projections. The coronavirus model's free balance and dependability emphasis are computed. Additionally, it is shown that a consistent, regular pattern exists. The outcomes are very good; we are getting them using the Matlab program. This model with order derivatives defined in this style had not previously been calculated. The changing system for this model is discussed. This model's best control and the number-based way of doing things for the test run that appears to have a control problem are also discussed.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"10 ","pages":"Article 100218"},"PeriodicalIF":0.0,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

(m1,m2)-pseudo almost periodic solutions of Clifford-valued high-order fuzzy cellular neural networks with time delays

Franklin Open Pub Date : 2025-01-15 DOI: 10.1016/j.fraope.2025.100215

Bing Li , Ting Chen , Yongkun Li

引用次数: 0