Franklin Open最新文献_第4页

DD-OCQAM: A spectrally efficient modulation scheme for in-vivo ultrasonic sensors DD-OCQAM：一种高效的体内超声传感器调制方案

Franklin Open

Pub Date : 2025-12-17 DOI: 10.1016/j.fraope.2025.100471

Ahmed A. Abouelfadl , Tamer Mekkawy

Reliable ultrasonic communication is essential for biomedical sensors in implantable medical devices, targeted drug delivery, and real-time physiological monitoring. However, in-vivo ultrasonic channels experience severe attenuation, multipath propagation, and scattering due to biological tissue heterogeneity, which limit data rate and reliability. While orthogonal chirp division multiplexing (OCDM) offers robustness against multipath interference, its high bandwidth requirement restricts applicability in sensor-based systems. This paper proposes dual-dictionary orthogonal chirp and QAM modulation (DD-OCQAM), a multidimensional signaling scheme that jointly encodes information in chirp rate and QAM symbols to enhance spectral efficiency and resilience. A theoretical framework is developed for symbol-error-rate (SER) analysis, establishing analytical bounds that remain valid in low-SNR regimes. Monte Carlo simulations confirm the theoretical results and demonstrate consistent BER improvements over OFDM across AWGN, flat, and frequency-selective fading channels. Experimental validation using measured in-vivo ultrasonic data (Bos et al., 2019), including gelatin implant-to-implant scenarios, further verifies the scheme’s practicality and sensitivity to the chirp dictionary size

N

. These results demonstrate that DD-OCQAM achieves a favorable trade-off between processing gain and bandwidth usage, contributing to the advancement of next-generation ultrasonic biomedical communication networks.

可靠的超声通信对于植入式医疗设备中的生物医学传感器、靶向药物输送和实时生理监测至关重要。然而，由于生物组织的异质性，体内超声通道会经历严重的衰减、多径传播和散射，这限制了数据速率和可靠性。虽然正交调频分复用（OCDM）具有抗多径干扰的鲁棒性，但其高带宽要求限制了其在传感器系统中的适用性。本文提出了双字典正交啁啾和QAM调制（DD-OCQAM），这是一种多维信令方案，它将啁啾率和QAM符号的信息联合编码，以提高频谱效率和弹性。为符号误码率（SER）分析开发了一个理论框架，建立了在低信噪比制度下仍然有效的分析界限。蒙特卡罗模拟证实了理论结果，并证明了在AWGN、平坦和频率选择性衰落信道上，OFDM的误码率改善是一致的。使用测量的体内超声数据进行实验验证（Bos等人，2019），包括明胶植入物到植入物的场景，进一步验证了该方案的实用性和对啁啾字典大小n的敏感性。这些结果表明，DD-OCQAM在处理增益和带宽使用之间实现了良好的权衡，有助于下一代超声生物医学通信网络的发展。

{"title":"DD-OCQAM: A spectrally efficient modulation scheme for in-vivo ultrasonic sensors","authors":"Ahmed A. Abouelfadl , Tamer Mekkawy","doi":"10.1016/j.fraope.2025.100471","DOIUrl":"10.1016/j.fraope.2025.100471","url":null,"abstract":"<div><div>Reliable ultrasonic communication is essential for biomedical sensors in implantable medical devices, targeted drug delivery, and real-time physiological monitoring. However, in-vivo ultrasonic channels experience severe attenuation, multipath propagation, and scattering due to biological tissue heterogeneity, which limit data rate and reliability. While orthogonal chirp division multiplexing (OCDM) offers robustness against multipath interference, its high bandwidth requirement restricts applicability in sensor-based systems. This paper proposes dual-dictionary orthogonal chirp and QAM modulation (DD-OCQAM), a multidimensional signaling scheme that jointly encodes information in chirp rate and QAM symbols to enhance spectral efficiency and resilience. A theoretical framework is developed for symbol-error-rate (SER) analysis, establishing analytical bounds that remain valid in low-SNR regimes. Monte Carlo simulations confirm the theoretical results and demonstrate consistent BER improvements over OFDM across AWGN, flat, and frequency-selective fading channels. Experimental validation using measured in-vivo ultrasonic data (Bos et al., 2019), including gelatin implant-to-implant scenarios, further verifies the scheme’s practicality and sensitivity to the chirp dictionary size <span><math><mi>N</mi></math></span>. These results demonstrate that DD-OCQAM achieves a favorable trade-off between processing gain and bandwidth usage, contributing to the advancement of next-generation ultrasonic biomedical communication networks.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100471"},"PeriodicalIF":0.0,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145798927","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}

引用次数: 0

Exploring the impact of fear, carry-over effects, and selective predation in a seasonally driven predator–prey system 探索恐惧的影响，在季节性驱动的捕食者-猎物系统中的携带效应和选择性捕食

Franklin Open

Pub Date : 2025-12-16 DOI: 10.1016/j.fraope.2025.100469

Samares Pal , Sasanka Shekhar Maity

In many ecological circumstances, fear of predation and its carry-over effects are crucial elements of the predator–prey system. Since predators can identify infected animals, they try to avoid prey that have a parasite infection to reduce fitness costs. Here, we consider a predator–prey eco-epidemic model that takes into account fear caused by selective predation and its carry-over effect. Assume that the disease is of the

S I

-

type. Using the carry-over effect as the potential bifurcation parameter, we address fundamental features such as boundedness, feasible equilibria and their stability, and Hopf bifurcation’s incidence in the analytical section. Validation of analytical results is done by numerical simulation. According to the results of our simulation, the intensity of fear and its carry-over effect might cause instability in the dynamics of a system. Increased predation fear due to disease leads to the elimination of persistent oscillations, restoring system stability. The feeding preference of predator can destabilize the system. We obtained a formula for the basic reproduction number (

R_{0}

). The disease-free equilibrium is stable for

R_{0} < 1

, whereas the endemic equilibrium appears for

R_{0} > 1

. In order to better accurately describe the aforementioned scenarios, we take into account the non-autonomous system by varying the parameters that show the strength of fear, the carry-over impact, the prevalence of disease, and the predators’ selective preference over time. Conditions for which the system has at least one positive periodic solution are found for the seasonally forced system. In our seasonally forced model, complex bursting patterns, higher periodic solutions, and a distinct periodic solution occur.

在许多生态环境中，对被捕食者的恐惧及其携带效应是捕食者-被捕食者系统的关键因素。由于捕食者可以识别受感染的动物，它们会尽量避开感染了寄生虫的猎物，以降低适应成本。在这里，我们考虑了一个捕食者-猎物生态流行病模型，该模型考虑了选择性捕食及其遗留效应引起的恐惧。以SI−型为例。在分析部分中，我们利用结转效应作为潜在分岔参数，讨论了有界性、可行平衡点及其稳定性、Hopf分岔发生率等基本特征。通过数值模拟对分析结果进行了验证。根据我们的模拟结果，恐惧的强度及其携带效应可能会导致系统动力学的不稳定。由于疾病引起的捕食恐惧增加导致持续振荡的消除，恢复系统稳定性。捕食者的摄食偏好会破坏系统的稳定性。我们得到了基本再生数（R0）的公式。R0>；1的无病平衡是稳定的，而R0>；1出现地方性平衡。为了更好地准确描述上述情景，我们通过改变显示恐惧强度、携带影响、疾病流行程度和捕食者随时间的选择偏好的参数来考虑非自治系统。对于季节强迫系统，找到了系统至少有一个正周期解的条件。在我们的季节强迫模型中，出现了复杂的爆发模式、较高的周期解和明显的周期解。

{"title":"Exploring the impact of fear, carry-over effects, and selective predation in a seasonally driven predator–prey system","authors":"Samares Pal , Sasanka Shekhar Maity","doi":"10.1016/j.fraope.2025.100469","DOIUrl":"10.1016/j.fraope.2025.100469","url":null,"abstract":"<div><div>In many ecological circumstances, fear of predation and its carry-over effects are crucial elements of the predator–prey system. Since predators can identify infected animals, they try to avoid prey that have a parasite infection to reduce fitness costs. Here, we consider a predator–prey eco-epidemic model that takes into account fear caused by selective predation and its carry-over effect. Assume that the disease is of the <span><math><mrow><mi>S</mi><mi>I</mi></mrow></math></span> <span><math><mo>−</mo></math></span> type. Using the carry-over effect as the potential bifurcation parameter, we address fundamental features such as boundedness, feasible equilibria and their stability, and Hopf bifurcation’s incidence in the analytical section. Validation of analytical results is done by numerical simulation. According to the results of our simulation, the intensity of fear and its carry-over effect might cause instability in the dynamics of a system. Increased predation fear due to disease leads to the elimination of persistent oscillations, restoring system stability. The feeding preference of predator can destabilize the system. We obtained a formula for the basic reproduction number (<span><math><msub><mrow><mi>R</mi></mrow><mrow><mn>0</mn></mrow></msub></math></span>). The disease-free equilibrium is stable for <span><math><mrow><msub><mrow><mi>R</mi></mrow><mrow><mn>0</mn></mrow></msub><mo><</mo><mn>1</mn></mrow></math></span>, whereas the endemic equilibrium appears for <span><math><mrow><msub><mrow><mi>R</mi></mrow><mrow><mn>0</mn></mrow></msub><mo>></mo><mn>1</mn></mrow></math></span>. In order to better accurately describe the aforementioned scenarios, we take into account the non-autonomous system by varying the parameters that show the strength of fear, the carry-over impact, the prevalence of disease, and the predators’ selective preference over time. Conditions for which the system has at least one positive periodic solution are found for the seasonally forced system. In our seasonally forced model, complex bursting patterns, higher periodic solutions, and a distinct periodic solution occur.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100469"},"PeriodicalIF":0.0,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145798981","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}

引用次数: 0

Novel flexible two-parameter sine modified Lindley distribution: Properties and application 新型柔性双参数正弦修正林德利分布：性质与应用

Franklin Open

Pub Date : 2025-12-15 DOI: 10.1016/j.fraope.2025.100467

Walaa A. El-Sharkawy , Khalid Ul Islam Rather

In this paper, we introduce a two-parameter sine modified Lindley distribution derived as a special case of the sine-exp-G family. Some statistical properties of the proposed distribution, including the quantile function; linear representations of the cumulative distribution, probability density function, and survival function; moments; moment generating function; incomplete moments; and order statistics are investigated. Parameter estimation is studied using both the maximum likelihood and method of moments approaches under complete and type II censored samples. A Monte Carlo simulation is conducted to compare the performance of the obtained estimates. Finally, two real data sets are presented to demonstrate the distribution’s flexibility and its superiority compared to competing Lindley-based distributions.

本文引入了正弦修正的双参数林德利分布，作为正弦exp- g族的一种特例。所提出分布的一些统计性质，包括分位数函数；累积分布、概率密度函数和生存函数的线性表示；时刻;矩生成函数；不完整的时刻;并对序统计量进行了研究。研究了在完全样本和II型截尾样本下，用极大似然法和矩量法进行参数估计。通过蒙特卡罗仿真来比较得到的估计的性能。最后，给出了两个真实数据集，以证明该分布的灵活性及其与基于lindley的竞争分布相比的优势。

引用次数: 0

Efficient shared secret key distribution using Cellular Automata for hybrid cryptosystems 混合密码系统中基于元胞自动机的有效共享密钥分配

Franklin Open

Pub Date : 2025-12-15 DOI: 10.1016/j.fraope.2025.100465

Biswarup Yogi , Ajoy Kumar Khan

The present work demonstrates that combining Elliptic Curve Cryptography and Cellular Automata Rule 90 for AES shared session key generation improves randomness, security strength, and computational efficiency. The proposed method uses ECC to generate a shared secret in binary form. CA Rule 90 expands this binary sequence into the key stream. AES then encrypts the input image using this hybrid session key. The system is developed and executed with standard benchmark images in Python. The results show that the mechanism is highly resistant to statistical and differential attacks. For example, the NPCR achieves 99.6916%, UACI reaches 49.5214% with the encrypted images having high entropy and high MSE values with almost no pixel correlation. The method is relatively fast, with an average encryption time of 0.000248 s, and has low memory and CPU utilisation. Based on the presented information, the ECC-CA hybrid model offers an efficient approach for providing lightweight security for IoT and resource-constrained devices.

本研究表明，结合椭圆曲线加密和元胞自动机规则90用于AES共享会话密钥生成，提高了随机性、安全强度和计算效率。该方法使用ECC生成二进制形式的共享密钥。CA规则90将这个二进制序列扩展到密钥流中。然后AES使用这个混合会话密钥对输入图像进行加密。该系统是用Python的标准基准图像开发和执行的。结果表明，该机制对统计攻击和差分攻击具有较强的抵抗能力。例如，NPCR达到99.6916%，UACI达到49.5214%，加密后的图像具有高熵和高MSE值，几乎没有像素相关性。该方法相对较快，平均加密时间为0.000248 s，并且内存和CPU利用率较低。基于所提供的信息，ECC-CA混合模型为物联网和资源受限设备提供了一种有效的轻量级安全性方法。

引用次数: 0

(μ1,μ2)-Pseudo almost periodic dynamics of hematopoiesis model with mixed delays and nonlinear harvesting term （μ1,μ2）-具有混合延迟和非线性收获项的造血模型伪概周期动力学

Franklin Open

Pub Date : 2025-12-15 DOI: 10.1016/j.fraope.2025.100450

Moez Ayachi

In this paper, we are interested to the dynamics of a generalized Hematopoiesis model involving mixed delays, nonlinear harvesting term and doubly-measure pseudo-almost periodic (

(μ_{1}, μ_{2}) - PAP

) parameters. By using the properties of

(μ_{1}, μ_{2}) - PAP

functions and the contraction mapping principle, suitable sufficient conditions were established for the existence, uniqueness and stability of

(μ_{1}, μ_{2}) - PAP

solution. Finally, a numerical example is presented to illustrate the theoretical findings. The results obtained in this paper provide a better understanding of the dynamics of hematopoiesis models with mixed delays and could be useful in further studies on hematopoiesis models.

在本文中，我们对涉及混合延迟、非线性收获项和双测量伪概周期（(μ1,μ2)−PAP）参数的广义造血模型的动力学问题感兴趣。利用(μ1,μ2)−PAP函数的性质和收缩映射原理，建立了(μ1,μ2)−PAP解的存在性、唯一性和稳定性的充分条件。最后，给出了一个数值算例来说明理论结果。本文的研究结果有助于更好地理解混合延迟的造血模型动力学，对进一步研究造血模型具有一定的指导意义。

{"title":"(μ1,μ2)-Pseudo almost periodic dynamics of hematopoiesis model with mixed delays and nonlinear harvesting term","authors":"Moez Ayachi","doi":"10.1016/j.fraope.2025.100450","DOIUrl":"10.1016/j.fraope.2025.100450","url":null,"abstract":"<div><div>In this paper, we are interested to the dynamics of a generalized Hematopoiesis model involving mixed delays, nonlinear harvesting term and doubly-measure pseudo-almost periodic (<span><math><mrow><mrow><mo>(</mo><msub><mrow><mi>μ</mi></mrow><mrow><mn>1</mn></mrow></msub><mo>,</mo><msub><mrow><mi>μ</mi></mrow><mrow><mn>2</mn></mrow></msub><mo>)</mo></mrow><mo>−</mo><mi>PAP</mi></mrow></math></span>) parameters. By using the properties of <span><math><mrow><mrow><mo>(</mo><msub><mrow><mi>μ</mi></mrow><mrow><mn>1</mn></mrow></msub><mo>,</mo><msub><mrow><mi>μ</mi></mrow><mrow><mn>2</mn></mrow></msub><mo>)</mo></mrow><mo>−</mo><mi>PAP</mi></mrow></math></span> functions and the contraction mapping principle, suitable sufficient conditions were established for the existence, uniqueness and stability of <span><math><mrow><mrow><mo>(</mo><msub><mrow><mi>μ</mi></mrow><mrow><mn>1</mn></mrow></msub><mo>,</mo><msub><mrow><mi>μ</mi></mrow><mrow><mn>2</mn></mrow></msub><mo>)</mo></mrow><mo>−</mo><mi>PAP</mi></mrow></math></span> solution. Finally, a numerical example is presented to illustrate the theoretical findings. The results obtained in this paper provide a better understanding of the dynamics of hematopoiesis models with mixed delays and could be useful in further studies on hematopoiesis models.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100450"},"PeriodicalIF":0.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145798984","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}

引用次数: 0

Securing wireless sensor networks: A survey of challenges and innovations 保护无线传感器网络：挑战和创新的调查

Franklin Open

Pub Date : 2025-12-14 DOI: 10.1016/j.fraope.2025.100470

R Sudha , M Premkumar

WSNs are a significant component of the modern technology systems. They find application in numerous sectors such as environmental monitoring, health care, agriculture and intelligent constructions. Although they possess low power, have low processing capacity and can readily be influenced by unsafe environments, they are still very important. They are therefore usually the victims of various forms of security threats as a result of that. The more advanced these threats become, the higher is the need to have strong and flexible security measures. The survey examines a broad spectrum of studies on the security of WSN. It encompasses numerous fields, such as how to transmit data safely, how to deal with keys, trust and reputation management systems and how to check and authenticate users. It also considers novel concepts such as applying blockchain and machine learning to identify security problems. Some of the studies in the research are based on straightforward solutions that can be applied effectively with the available limited resources of WSNs, whereas others attempt to achieve the balance between security and efficiency. Despite these developments, there are issues. The solutions are mostly energy consuming or are rigid to adapt to changing network conditions. The disconnect between the concepts in studies and their practical implementation is also present, in particular, the use of complex technologies, such as AI, in practice. This review aims to unite significant conclusions of the recent research, to emphasize the main issues that are not resolved yet, and to propose the useful directions in the further investigations. This survey provides an up-to-date and clear image of the current trends in WSN security, as it allows the researcher and developers to develop more efficient and profound strategies on how to make the system stronger and more reliable.

无线传感器网络是现代技术系统的重要组成部分。它们在环境监测、医疗保健、农业和智能建筑等众多领域都有应用。虽然它们功率低，处理能力低，而且容易受到不安全环境的影响，但它们仍然非常重要。因此，他们通常是各种形式的安全威胁的受害者。这些威胁变得越先进，就越需要强大而灵活的安全措施。该调查对无线传感器网络的安全性进行了广泛的研究。它涵盖了许多领域，例如如何安全地传输数据，如何处理密钥，信任和声誉管理系统以及如何检查和认证用户。它还考虑了一些新颖的概念，比如应用区块链和机器学习来识别安全问题。研究中的一些研究是基于直接的解决方案，可以有效地利用有限的可用WSNs资源，而另一些研究则试图在安全性和效率之间取得平衡。尽管取得了这些进展，但仍存在一些问题。这些解决方案大多能耗大，或者难以适应不断变化的网络条件。研究中的概念与其实际实施之间也存在脱节，特别是在实践中使用人工智能等复杂技术时。本文综述了近年来研究的重要结论，强调了尚未解决的主要问题，并提出了今后研究的有益方向。这项调查提供了一个最新的和清晰的图像，当前的趋势在无线传感器网络的安全，因为它允许研究人员和开发人员制定更有效和深刻的策略，如何使系统更强大和更可靠。

{"title":"Securing wireless sensor networks: A survey of challenges and innovations","authors":"R Sudha , M Premkumar","doi":"10.1016/j.fraope.2025.100470","DOIUrl":"10.1016/j.fraope.2025.100470","url":null,"abstract":"<div><div>WSNs are a significant component of the modern technology systems. They find application in numerous sectors such as environmental monitoring, health care, agriculture and intelligent constructions. Although they possess low power, have low processing capacity and can readily be influenced by unsafe environments, they are still very important. They are therefore usually the victims of various forms of security threats as a result of that. The more advanced these threats become, the higher is the need to have strong and flexible security measures. The survey examines a broad spectrum of studies on the security of WSN. It encompasses numerous fields, such as how to transmit data safely, how to deal with keys, trust and reputation management systems and how to check and authenticate users. It also considers novel concepts such as applying blockchain and machine learning to identify security problems. Some of the studies in the research are based on straightforward solutions that can be applied effectively with the available limited resources of WSNs, whereas others attempt to achieve the balance between security and efficiency. Despite these developments, there are issues. The solutions are mostly energy consuming or are rigid to adapt to changing network conditions. The disconnect between the concepts in studies and their practical implementation is also present, in particular, the use of complex technologies, such as AI, in practice. This review aims to unite significant conclusions of the recent research, to emphasize the main issues that are not resolved yet, and to propose the useful directions in the further investigations. This survey provides an up-to-date and clear image of the current trends in WSN security, as it allows the researcher and developers to develop more efficient and profound strategies on how to make the system stronger and more reliable.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100470"},"PeriodicalIF":0.0,"publicationDate":"2025-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145798985","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}

引用次数: 0

Modelling and design optimization of switched reluctance motors based on machine learning methods: Review 基于机器学习方法的开关磁阻电机建模与优化设计综述

Franklin Open

Pub Date : 2025-12-14 DOI: 10.1016/j.fraope.2025.100474

Jackson Oloo, Laszlo Szamel

Accurate modelling of Switched Reluctance Motors (SRM) is a complex and time consuming task that involves a lot of tradeoffs and assumptions. Numerical and analytical modelling techniques have been extensively used in literature. Due to recent advancements in artificial intelligence and machine learning (ML) methods, there is need to explore nonlinear modelling of SRMs using machine learning surrogate models. This paper presents a comprehensive review of machine learning techniques of optimizing Switched Reluctance Motor (SRM) models. Several machine learning models have been developed to optimize SRM parameters such as stator pole arc, rotor pole arc, stack length, turns per pole, and phase current. The SRM parameter values have been obtained from Finite Element Analysis data of an 8/6, 600 V machine. The design parameters are optimized based on weighted combination objective function. The objective is to minimize torque ripples while maximizing efficiency. The ML techniques considered in this work include the Bayesian algorithm, Feed Forward Neural Network (FNN), Back Propagation Neural Network (BPNN), Artificial Neural Network (ANN), Radial Basis Function Neural Network (RBFNN), Sequential Least Squares Programming (SLSP) and Gaussian Process Regressor (GPR). The BPNN is trained with various techniques such as Levenberg Marquardt (LM), Differential Evolution (DE), Gradient Descent Algorithm (GDA), Quasi-Newton algorithm, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Best parameters, percentage torque ripple reduction and percentage efficiency improvement are then used to evaluate the performance of the machine learning optimization models.

开关磁阻电机（SRM）的精确建模是一项复杂而耗时的任务，涉及许多权衡和假设。数值和分析建模技术已在文献中广泛使用。由于人工智能和机器学习（ML）方法的最新进展，需要使用机器学习代理模型探索srm的非线性建模。本文综述了用于优化开关磁阻电机模型的机器学习技术。已经开发了几个机器学习模型来优化SRM参数，如定子极弧、转子极弧、堆叠长度、每极匝数和相电流。从一台8/ 6,600 V电机的有限元分析数据中得到了SRM参数值。基于加权组合目标函数对设计参数进行优化。目标是在最大限度地提高效率的同时最小化扭矩波动。本研究中考虑的机器学习技术包括贝叶斯算法、前馈神经网络（FNN）、反向传播神经网络（BPNN）、人工神经网络（ANN）、径向基函数神经网络（RBFNN）、顺序最小二乘规划（SLSP）和高斯过程回归器（GPR）。BPNN使用各种技术进行训练，如Levenberg Marquardt （LM）、差分进化（DE）、梯度下降算法（GDA）、准牛顿算法、遗传算法（GA）和粒子群优化（PSO）。然后使用最佳参数、扭矩脉动减少百分比和效率提高百分比来评估机器学习优化模型的性能。

{"title":"Modelling and design optimization of switched reluctance motors based on machine learning methods: Review","authors":"Jackson Oloo, Laszlo Szamel","doi":"10.1016/j.fraope.2025.100474","DOIUrl":"10.1016/j.fraope.2025.100474","url":null,"abstract":"<div><div>Accurate modelling of Switched Reluctance Motors (SRM) is a complex and time consuming task that involves a lot of tradeoffs and assumptions. Numerical and analytical modelling techniques have been extensively used in literature. Due to recent advancements in artificial intelligence and machine learning (ML) methods, there is need to explore nonlinear modelling of SRMs using machine learning surrogate models. This paper presents a comprehensive review of machine learning techniques of optimizing Switched Reluctance Motor (SRM) models. Several machine learning models have been developed to optimize SRM parameters such as stator pole arc<strong>,</strong> rotor pole arc<strong>,</strong> stack length<strong>,</strong> turns per pole<strong>,</strong> and phase current<strong>.</strong> The SRM parameter values have been obtained from Finite Element Analysis data of an 8/6, 600 V machine. The design parameters are optimized based on weighted combination objective function. The objective is to minimize torque ripples while maximizing efficiency. The ML techniques considered in this work include the Bayesian algorithm, Feed Forward Neural Network (FNN), Back Propagation Neural Network (BPNN), Artificial Neural Network (ANN), Radial Basis Function Neural Network (RBFNN), Sequential Least Squares Programming (SLSP) and Gaussian Process Regressor (GPR). The BPNN is trained with various techniques such as Levenberg Marquardt (LM), Differential Evolution (DE), Gradient Descent Algorithm (GDA), Quasi-Newton algorithm, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Best parameters, percentage torque ripple reduction and percentage efficiency improvement are then used to evaluate the performance of the machine learning optimization models.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100474"},"PeriodicalIF":0.0,"publicationDate":"2025-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885156","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}

引用次数: 0

AI-driven model for knee cartilage degeneration using SAM, Swin, Grad-CAM, and CapsNet 人工智能驱动的膝关节软骨退变模型使用SAM， Swin， Grad-CAM和CapsNet

Franklin Open

Pub Date : 2025-12-14 DOI: 10.1016/j.fraope.2025.100472

Simran , Vinay Kukreja , Vandana Ahuja , Shiva Mehta , Ankit Banal

Context

Knee cartilage degeneration is a major contributor to mobility disability, and affects millions of individuals worldwide. For effective intervention, early accurate detection of the condition is essential. Conventional approaches often lack sufficient sensitivity, whereas recent artificial intelligence (AI) techniques have demonstrated improved diagnostic accuracy.

Objective

The study aims to develop an AI-based model for accurate classification of knee cartilage degeneration stages, integrating segmentation, feature extraction, and classification techniques to address existing limitations.

Methodology

The proposed model employs the Segment Anything Model (SAM) for segmentation, the Swin Transformer for feature extraction, and a Capsule Network (CapsNet) for classification.The Dice Similarity Coefficient (DSC) and Intersection Over Union (IoU) were used to evaluate the segmentation's performance. For classification, accuracy, precision, recall, and F1-score were used. Gradient-weighted class activation mapping (Grad-CAM) was employed to support interpretability.

Results

Segmentation achieved a DSC of 0.90 and IoU of 0.83, enabling accurate extraction of cartilage regions. Grad-CAM correlation values ranged from 0.85 to 0.89, indicating consistent localization of relevant cartilage regions. Classification accuracy reached 96.5% for healthy, 94.8% for mild, 95.2% for moderate, and 93.7% for severe cases, with corresponding F1-scores ranging from 93.0% (severe) to 96.0% (healthy). Overall, the proposed model achieved an accuracy of 97%, with a precision of 96% and a recall of 95%, demonstrating robust performance across all evaluation metrics.

Future scope

Future work includes expanding dataset diversity, exploring multimodal approaches, and implementing real-time clinical applications to enhance diagnostic accuracy and personalized treatment planning.

膝关节软骨退行性变是导致行动障碍的主要原因，影响着全世界数百万人。为了有效的干预，早期准确的检测是必不可少的。传统方法往往缺乏足够的灵敏度，而最近的人工智能（AI）技术已经证明了更高的诊断准确性。目的建立基于人工智能的膝关节软骨退变分期准确分类模型，整合分割、特征提取和分类技术，解决现有的局限性。该模型采用分段任意模型（SAM）进行分割，Swin变压器进行特征提取，胶囊网络（CapsNet）进行分类。使用Dice Similarity Coefficient （DSC）和Intersection Over Union （IoU）来评价分割效果。分类采用准确率、精密度、召回率和f1评分。梯度加权类激活映射（Grad-CAM）用于支持可解释性。结果分割的DSC为0.90，IoU为0.83，能够准确提取软骨区域。Grad-CAM相关值为0.85 ~ 0.89，表明相关软骨区域定位一致。健康组、轻度组、中度组、重度组的分类准确率分别为96.5%、94.8%、95.2%、93.7%，对应的f1评分范围为93.0%（重度）~ 96.0%（健康）。总体而言，所提出的模型实现了97%的准确率，96%的精度和95%的召回率，在所有评估指标中表现出稳健的性能。未来的工作范围未来的工作包括扩大数据集的多样性，探索多模式方法，实施实时临床应用，以提高诊断准确性和个性化治疗计划。

{"title":"AI-driven model for knee cartilage degeneration using SAM, Swin, Grad-CAM, and CapsNet","authors":"Simran , Vinay Kukreja , Vandana Ahuja , Shiva Mehta , Ankit Banal","doi":"10.1016/j.fraope.2025.100472","DOIUrl":"10.1016/j.fraope.2025.100472","url":null,"abstract":"<div><h3>Context</h3><div>Knee cartilage degeneration is a major contributor to mobility disability, and affects millions of individuals worldwide. For effective intervention, early accurate detection of the condition is essential. Conventional approaches often lack sufficient sensitivity, whereas recent artificial intelligence (AI) techniques have demonstrated improved diagnostic accuracy.</div></div><div><h3>Objective</h3><div>The study aims to develop an AI-based model for accurate classification of knee cartilage degeneration stages, integrating segmentation, feature extraction, and classification techniques to address existing limitations.</div></div><div><h3>Methodology</h3><div>The proposed model employs the Segment Anything Model (SAM) for segmentation, the Swin Transformer for feature extraction, and a Capsule Network (CapsNet) for classification.The Dice Similarity Coefficient (DSC) and Intersection Over Union (IoU) were used to evaluate the segmentation's performance. For classification, accuracy, precision, recall, and F1-score were used. Gradient-weighted class activation mapping (Grad-CAM) was employed to support interpretability.</div></div><div><h3>Results</h3><div>Segmentation achieved a DSC of 0.90 and IoU of 0.83, enabling accurate extraction of cartilage regions. Grad-CAM correlation values ranged from 0.85 to 0.89, indicating consistent localization of relevant cartilage regions. Classification accuracy reached 96.5% for healthy, 94.8% for mild, 95.2% for moderate, and 93.7% for severe cases, with corresponding F1-scores ranging from 93.0% (severe) to 96.0% (healthy). Overall, the proposed model achieved an accuracy of 97%, with a precision of 96% and a recall of 95%, demonstrating robust performance across all evaluation metrics.</div></div><div><h3>Future scope</h3><div>Future work includes expanding dataset diversity, exploring multimodal approaches, and implementing real-time clinical applications to enhance diagnostic accuracy and personalized treatment planning.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100472"},"PeriodicalIF":0.0,"publicationDate":"2025-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885080","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}

引用次数: 0

Explainable AI for SMS spam filtering: A novel hybrid architecture combining fuzzy logic and bidirectional LSTM networks 用于短信垃圾邮件过滤的可解释人工智能：一种结合模糊逻辑和双向LSTM网络的新型混合架构

Franklin Open

Pub Date : 2025-12-13 DOI: 10.1016/j.fraope.2025.100466

Ali kadhim Jasim , Fuqdan Abdul Fadil Al-ibeahimi , Hussein Alaa Alkaabi

SMS spam filtering has become a critical application in modern telecommunications, where unsolicited and fraudulent text messages compromise user security, erode trust, and burden network resources. To address these challenges, this study proposes a novel hybrid architecture that integrates fuzzy logic with a bidirectional long short-term memory (BiLSTM) network to achieve high classification performance and transparent decision-making. The fuzzy logic module captures linguistic uncertainty using Gaussian membership functions, while the BiLSTM effectively models sequential dependencies in text. To further enhance interpretability, token-level attention highlights influential words, and rule-based explanations provide human-understandable justifications for each classification outcome. The proposed framework was evaluated on two benchmark datasets: the UCI SMS Spam Collection and the ExAIS_SMS dataset. Experimental results demonstrate strong performance, with accuracies of 99.4 % and 95.8 %, respectively, outperforming several baseline approaches. Notably, the model also achieves high discriminative capability, with AUC values of 0.994 and 0.980 across the two datasets. Beyond accuracy, the framework is computationally efficient, requiring <2.5 GB of memory and averaging under 7 ms per message during inference on a consumer-grade GPU. This ensures feasibility for real-time, large-scale deployment. By balancing accuracy, interpretability, and efficiency, the proposed fuzzy-deep hybrid approach offers a practical and trustworthy solution for SMS spam detection in telecom environments.

短信垃圾邮件过滤已成为现代电信中的一项重要应用，未经请求的和欺诈性的短信危及用户安全，侵蚀信任，并增加网络资源的负担。为了解决这些挑战，本研究提出了一种新的混合架构，将模糊逻辑与双向长短期记忆（BiLSTM）网络相结合，以实现高分类性能和透明决策。模糊逻辑模块使用高斯隶属函数捕获语言的不确定性，而BiLSTM则有效地对文本中的顺序依赖关系进行建模。为了进一步提高可解释性，标记级关注突出了有影响力的单词，基于规则的解释为每个分类结果提供了人类可理解的理由。该框架在两个基准数据集上进行了评估：UCI SMS Spam Collection和ExAIS_SMS数据集。实验结果显示了较强的性能，准确率分别为99.4%和95.8%，优于几种基线方法。值得注意的是，该模型也实现了很高的判别能力，两个数据集的AUC值分别为0.994和0.980。除了准确性之外，该框架的计算效率很高，需要2.5 GB的内存，在消费级GPU上进行推理时，平均每条消息低于7毫秒。这确保了实时、大规模部署的可行性。通过平衡准确性、可解释性和效率，本文提出的模糊深度混合方法为电信环境下的短信垃圾检测提供了一种实用、可靠的解决方案。

{"title":"Explainable AI for SMS spam filtering: A novel hybrid architecture combining fuzzy logic and bidirectional LSTM networks","authors":"Ali kadhim Jasim , Fuqdan Abdul Fadil Al-ibeahimi , Hussein Alaa Alkaabi","doi":"10.1016/j.fraope.2025.100466","DOIUrl":"10.1016/j.fraope.2025.100466","url":null,"abstract":"<div><div>SMS spam filtering has become a critical application in modern telecommunications, where unsolicited and fraudulent text messages compromise user security, erode trust, and burden network resources. To address these challenges, this study proposes a novel hybrid architecture that integrates fuzzy logic with a bidirectional long short-term memory (BiLSTM) network to achieve high classification performance and transparent decision-making. The fuzzy logic module captures linguistic uncertainty using Gaussian membership functions, while the BiLSTM effectively models sequential dependencies in text. To further enhance interpretability, token-level attention highlights influential words, and rule-based explanations provide human-understandable justifications for each classification outcome. The proposed framework was evaluated on two benchmark datasets: the UCI SMS Spam Collection and the ExAIS_SMS dataset. Experimental results demonstrate strong performance, with accuracies of 99.4 % and 95.8 %, respectively, outperforming several baseline approaches. Notably, the model also achieves high discriminative capability, with AUC values of 0.994 and 0.980 across the two datasets. Beyond accuracy, the framework is computationally efficient, requiring <2.5 GB of memory and averaging under 7 ms per message during inference on a consumer-grade GPU. This ensures feasibility for real-time, large-scale deployment. By balancing accuracy, interpretability, and efficiency, the proposed fuzzy-deep hybrid approach offers a practical and trustworthy solution for SMS spam detection in telecom environments.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100466"},"PeriodicalIF":0.0,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885255","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}

引用次数: 0

Operational stability maps for climate-driven predator–prey dynamics: Distributed-order memory & hopf shifts 气候驱动的捕食者-猎物动态的操作稳定性图：分布式顺序记忆和hopf移位

Franklin Open

Pub Date : 2025-12-13 DOI: 10.1016/j.fraope.2025.100460

Randhir Singh Baghel

We develop a distributed-order fractional predator-prey model that incorporates climate-driven thermal forcing, fear-mediated behavioural suppression, and memory-dependent vigilance dynamics. The model is governed by the distributed-order Caputo operator

^{C} D_{t}^{(μ)} x (t) = \int_{0}^{1} μ {(α)}^{C} D_{t}^{α} x (t) d α,

which captures a continuum of ecological memory scales. Temperature-dependent demographic rates

r (T)

,

a (T)

, and

μ (T)

modulate growth, predation, and mortality, while the dynamic fear variable

f (t)

reduces prey reproduction and encounter rates. We derive positivity, boundedness, and equilibrium conditions, and characterize the onset of oscillations via the Hopf bifurcation threshold

G^{*}

. Stability analysis shows that distributed-order memory shifts Hopf boundaries and modifies invasion thresholds compared with the classical integer-order limit. A global sensitivity analysis using partial rank correlation coefficients (PRCC) and Sobol indices identifies temperature elasticities

θ_{r}

,

θ_{β}

, and

θ_{μ}

as dominant drivers of the predator invasion number

R_{y}

, while fear suppression

s_{p}

and low-order memory weights strongly influence

G^{*}

. A climate-driven zooplankton-phytoplankton case study illustrates how warming and behavioural feedback jointly shape predator-prey resilience, highlighting scenarios in which distributed-order memory dampens oscillations and expands the region of stable coexistence.

我们开发了一个分布式顺序分数捕食者-猎物模型，该模型结合了气候驱动的热强迫，恐惧介导的行为抑制和记忆依赖的警戒动态。该模型由分布阶Caputo算子cdt (μ)x(t)=∫01μ(α)CDtαx(t)dα控制，该算子捕获了连续的生态记忆尺度。温度相关的人口统计率r(T)、a(T)和μ(T)调节生长、捕食和死亡率，而动态恐惧变量f(T)降低猎物繁殖和遭遇率。我们导出了正性、有界性和平衡条件，并通过Hopf分岔阈值G*描述了振荡的开始。稳定性分析表明，与传统的整数阶极限相比，分布式记忆改变了Hopf边界，改变了入侵阈值。利用偏秩相关系数（PRCC）和Sobol指数进行全局敏感性分析，发现温度弹性θr、θβ和θμ是捕食者入侵数Ry的主要驱动因素，而恐惧抑制sp和低阶记忆权值对G*有强烈影响。气候驱动的浮游动物-浮游植物案例研究说明了变暖和行为反馈如何共同塑造捕食者-猎物的恢复力，突出了分布式顺序记忆抑制振荡并扩大稳定共存区域的情景。

{"title":"Operational stability maps for climate-driven predator–prey dynamics: Distributed-order memory & hopf shifts","authors":"Randhir Singh Baghel","doi":"10.1016/j.fraope.2025.100460","DOIUrl":"10.1016/j.fraope.2025.100460","url":null,"abstract":"<div><div>We develop a distributed-order fractional predator-prey model that incorporates climate-driven thermal forcing, fear-mediated behavioural suppression, and memory-dependent vigilance dynamics. The model is governed by the distributed-order Caputo operator</div><div><span><math><mrow><msup><mrow></mrow><mi>C</mi></msup><msubsup><mi>D</mi><mi>t</mi><mrow><mo>(</mo><mi>μ</mi><mo>)</mo></mrow></msubsup><mi>x</mi><mrow><mo>(</mo><mi>t</mi><mo>)</mo></mrow><mo>=</mo><munderover><mo>∫</mo><mrow><mn>0</mn></mrow><mn>1</mn></munderover><mrow><mi>μ</mi><msup><mrow><mrow><mo>(</mo><mi>α</mi><mo>)</mo></mrow></mrow><mi>C</mi></msup><msubsup><mi>D</mi><mi>t</mi><mi>α</mi></msubsup><mi>x</mi><mrow><mo>(</mo><mi>t</mi><mo>)</mo></mrow><mspace></mspace><mi>d</mi><mi>α</mi><mo>,</mo></mrow></mrow></math></span></div><div>which captures a continuum of ecological memory scales. Temperature-dependent demographic rates <span><math><mrow><mi>r</mi><mo>(</mo><mi>T</mi><mo>)</mo></mrow></math></span>, <span><math><mrow><mi>a</mi><mo>(</mo><mi>T</mi><mo>)</mo></mrow></math></span>, and <span><math><mrow><mi>μ</mi><mo>(</mo><mi>T</mi><mo>)</mo></mrow></math></span> modulate growth, predation, and mortality, while the dynamic fear variable <span><math><mrow><mi>f</mi><mo>(</mo><mi>t</mi><mo>)</mo></mrow></math></span> reduces prey reproduction and encounter rates. We derive positivity, boundedness, and equilibrium conditions, and characterize the onset of oscillations via the Hopf bifurcation threshold <span><math><msup><mrow><mi>G</mi></mrow><mo>*</mo></msup></math></span>. Stability analysis shows that distributed-order memory shifts Hopf boundaries and modifies invasion thresholds compared with the classical integer-order limit. A global sensitivity analysis using partial rank correlation coefficients (PRCC) and Sobol indices identifies temperature elasticities <span><math><msub><mi>θ</mi><mi>r</mi></msub></math></span>, <span><math><msub><mi>θ</mi><mi>β</mi></msub></math></span>, and <span><math><msub><mi>θ</mi><mi>μ</mi></msub></math></span> as dominant drivers of the predator invasion number <span><math><msub><mi>R</mi><mi>y</mi></msub></math></span>, while fear suppression <span><math><msub><mi>s</mi><mi>p</mi></msub></math></span> and low-order memory weights strongly influence <span><math><msup><mrow><mi>G</mi></mrow><mo>*</mo></msup></math></span>. A climate-driven zooplankton-phytoplankton case study illustrates how warming and behavioural feedback jointly shape predator-prey resilience, highlighting scenarios in which distributed-order memory dampens oscillations and expands the region of stable coexistence.</div></div>","PeriodicalId":100554,"journal":{"name":"Franklin Open","volume":"14 ","pages":"Article 100460"},"PeriodicalIF":0.0,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885153","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}

引用次数: 0