Fractional-order four-wing (FO 4-wing) systems are of significant importance due to their complex dynamics and wide-ranging applications in secure communications, encryption, and nonlinear circuit design, making their control and stabilization a critical area of study. In this research, a novel model-free finite-time flexible sliding mode control (FTF-SMC) strategy is developed for the stabilization of a particular category of hyperchaotic FO 4-wing systems, which are subject to unknown uncertainties and input saturation constraints. The proposed approach leverages fractional-order Lyapunov stability theory to design a flexible sliding mode controller capable of effectively addressing the chaotic dynamics of FO 4-wing systems and ensuring finite-time convergence. Initially, a dynamic sliding surface is formulated to accommodate system variations. Following this, a robust model-free control law is designed to counteract uncertainties and input saturation effects. The finite-time stability of both the sliding surface and the control scheme is rigorously proven. The control strategy eliminates the need for explicit system models by exploiting the norm-bounded characteristics of chaotic system states. To optimize the parameters of the model-free FTF-SMC, a deep reinforcement learning framework based on the adaptive dynamic programming (ADP) algorithm is employed. The ADP agent utilizes two neural networks (NNs)—action NN and critic NN—aiming to obtain the optimal policy by maximizing a predefined reward function. This ensures that the sliding motion satisfies the reachability condition within a finite time frame. The effectiveness of the proposed methodology is validated through comprehensive simulations, numerical case studies, and comparative analyses.

Background: Skin cancer is one of the most prevalent cancers worldwide. In the clinical domain, skin lesions such as melanoma detection are still a challenge due to occlusions, poor contrast, poor image quality, and similarities between skin lesions. Deep-/machine-learning methods are used for the early, accurate, and efficient detection of skin lesions. Therefore, we propose a boundary-aware segmentation network (BASNet) model comprising prediction and residual refinement modules.Materials and methods: The prediction module works like a U-Net and is densely supervised by an encoder and decoder. A hybrid loss function is used, which has the potential to help in the clinical domain of dermatology. BASNet handles these challenges by providing robust outcomes, even in suboptimal imaging environments. This leads to accurate early diagnosis, improved treatment outcomes, and efficient clinical workflows. We further propose a compact convolutional transformer model (CCTM) based on convolution and transformers for classification. This was designed on a selected number of layers and hyperparameters having two convolutions, two transformers, 64 projection dimensions, tokenizer, position embedding, sequence pooling, MLP, 64 batch size, two heads, 0.1 stochastic depth, 0.001 learning rate, 0.0001 weight decay, and 100 epochs.Results: The CCTM model was evaluated on six skin-lesion datasets, namely MED-NODE, PH2, ISIC-2019, ISIC-2020, HAM10000, and DermNet datasets, achieving over 98% accuracy.Conclusion: The proposed model holds significant potential in the clinical domain. Its ability to combine local feature extraction and global context understanding makes it ideal for tasks like medical image analysis and disease diagnosis.

This paper proposes a novel fixed-time prescribed performance sliding mode control method, specifically designed to address trajectory tracking issues in wheeled mobile robots (WMRs) affected by wheel slipping, skidding (WSS), and external disturbances. A new prescribed performance sliding surface is first introduced based on a prescribed performance function (PPF) and a non-singular fast terminal sliding function (NFTSF). This design ensures that tracking errors converge to zero within a fixed time while maintaining stability by keeping error states within predefined limits. A novel fixed-time prescribed performance non-singular fast terminal sliding mode control (FPP-NFTSMC) algorithm is proposed based on the sliding function. The control method integrates a uniform second-order sliding mode (USOSM) algorithm to provide a continuous control signal, effectively reducing the chattering effect. This method combines the benefits of PPF, NFTSMC, and USOSM algorithm to achieve high-precision position tracking, minimize chattering, guarantee fixed-time convergence, ensure tracking errors remain within bounds, and maintain robustness against WSS, and external disturbances. The fixed-time stability of the WMR systems is demonstrated by the Lyapunov stability theory. The effectiveness of the proposed method is validated through simulations of tracking straight-line and U-shaped trajectories.

This study proposed a new model to estimate the manual steering torque of steer-by-wire systems. The current steer-by-wire system uses the steering-actuator torque at the end of the rack-and-pinion gear to obtain the manual steering torque. However, there is a need for a new method to obtain the manual steering torque because a steer-by-wire system is expected to develop as it eliminates or at least simplifies more mechanical parts in order to enable them to be combined with other technologies such as an in-wheel motor. In order to propose a new estimation model, this study employs vehicle dynamics modeling and steering-system modeling. Vehicle dynamics modeling is used to estimate the self-aligning moment that arises between the tires and the ground. The slip angle and the normal force, as well as the tire properties of the vehicle, were considered to obtain the self-aligning moment. In addition, the steering system was also considered in this study because the calculated self-aligning moment is transferred through the steering system. The universal joint, the rack-and-pinion gear, and the lower-body linkages were modeled to calculate the manual steering torque delivered to the driver’s hands. For validation of the new model, there are two sets of simulation and verification processes in this study. First, the steering-system model was verified through experiments. A steering system was set as the target system, and its mechanical characteristics such as the inertial coefficient, the damping coefficient, and the stiffness were adopted for modeling and verification. Second, the manual steering torque estimation model was verified using field tests. A vehicle was set as the target vehicle, and its specifications such as the dimensions, the steering system, and the lower-body linkages were adopted for modeling and verification. The verification results were presented and show accurate estimation results. The new model proposed in this study does not need mechanical parts to estimate the manual steering torque apart from the steering actuator and the steering feedback actuator and, therefore, it can contribute to the development of a steer-by-wire system.

Accurately identifying apple diseases is essential to control their spread and support the industry. Timely and precise detection is crucial for managing the spread of diseases, thereby improving the production and quality of apples. However, the development of algorithms for analyzing complex leaf images remains a significant challenge. Therefore, in this study, a lightweight deep learning model is designed from scratch to identify the apple leaf condition. The developed framework comprises two stages. First, the designed 37-layer model was employed to assess the condition of apple leaves (healthy or diseased). Second, transfer learning was used for further subclassification of the disease class (e.g., rust, complex, scab, and frogeye leaf spots). The trained lightweight model was reused because the model trained with correlated images facilitated transfer learning for further classification of the disease class. A dataset available online was used to validate the proposed two-stage framework, resulting in a classification rate of 98.25% for apple leaf condition identification and an accuracy of 98.60% for apple leaf disease diagnosis. Furthermore, the results confirm that the proposed model is lightweight and involves relatively fewer learnable parameters in comparison with other pre-trained deep learning models.

This study proposes a new generated axial force (GAF) estimation model of tripod-type constant velocity (CV) joints. For development of the model, kinematic analysis was performed to derive the relative coordinates of components and contact points. Through the analysis, the normal load that acts on contact points was also obtained. This study employs two friction models—pure sliding and rolling–sliding—to obtain the friction coefficients on the contact points. Particularly for the rolling–sliding model, this study used the experimental analysis on rolling–sliding ratio and friction coefficients were studied using a tribometer. By introducing two models, this study considers not only the pure sliding friction but also the rolling–sliding friction that occurs between spherical rollers and tracks. This study verifies the GAF estimation model by comparing the simulation results with the experimental results. A tripod-type CV joint was set as a target and its GAF was derived by the model. Then, its actual GAF was measured and the results were compared with each other. A GAF measurement system was set up for the measurement in this study. The estimated results show similar trends with the measured results under low-resistance torque condition and the GAF model provides very accurate estimation under high-resistance torque conditions.