Search

Imperialist competitive algorithm (ICA) is an efficient meta-heuristic algorithm by simulating the competitive behaviour among imperialist countries. However, it still suffers from slow convergence and deficiency in exploration. To address these issues, an improved ICA is proposed by combining ICA with a quasi-opposition-based learning (QOBL) strategy, which is named QOBL-ICA. The improvements include two aspects. First, the QOBL strategy is adopted to generate a population of fitter individuals. Second, a QOBL-assisted assimilation strategy is proposed to enhance the exploration ability of ICA. As a result, the proposed QOBL-ICA has more powerful exploration ability than ICA as well as faster convergence speed. The effectiveness of the proposed QOBL-ICA is verified by testing on 20 benchmark functions and 3 engineering design problems. Experimental results show that the performance of QOBL-ICA is superior to most state-of-the-art meta-heuristic algorithms in terms of global optimum reached and convergence speed.

The rise of cyber threats, particularly URL-based phishing attacks, has tarnished the digital age despite its unparalleled access to information. These attacks often deceive users into disclosing confidential information by redirecting them to fraudulent websites. Existing browser-based methods, predominantly relying on blacklist approaches, have failed to effectively detect phishing attacks. To counteract this issue, we propose a novel system that integrates a deep learning model with a user-centric Chrome browser extension to detect and alert users about potential phishing URLs instantly. Our approach introduces a Knowledge Distilled ELECTRA model for URL detection and achieves remarkable performance metrics of 99.74% accuracy and a 99.43% F1-score on a diverse dataset of 450,176 URLs. Coupled with the browser extension, our system provides real-time feedback, empowering users to make informed decisions about the websites they visit. Additionally, we incorporate a user feedback loop for continuous model enhancement. This work sets a precedent by offering a seamless, robust, and efficient solution to mitigate phishing threats for internet users.

This work modifies the architecture of conventional CNN with the integration of Multi-resolution Analysis (MRA) in a CNN framework for Diabetic Retinopathy (DR) diagnosis and grading. Here, the HF sub-bands are subjected to optimized activations and are directly fed to the fully connected layers, as it encompasses edge features. Unlike FD-Relu, the proposed function preserves significant negative coefficients, compared to the S-Relu, the proposed third-order S-Relu is optimized such that it sustains the activations in the range suitable for the wavelet coefficients. The coefficients of higher-order terms of the proposed 3rd-order S-Relu are optimized with PSO, fitting the maximum energy of the wavelet sub-bands to ensure High Frequency (HF) edge preservation. The authors re-architecture 3 different CNNs published in the Retinal Image analysis field, with spatial and wavelet inputs with optimized activations. The highest accuracy of 96% is attained with the AlexNet re-architecture, with 35,126 fundus images secured from the Kaggle dataset. As we can infer the proposed re-architecture wavelet CNN outperformed the multiscale shallow CNNs, multiscale attention net, and stacked CNNs with a 6.6, 0.3, 0.7 per cent increase in accuracy. The entire implementation of the wavelet CNN is made available under source code.

Medical Thermography image is used for the detection of breast cancer at an earlier stage. Thermography image shows the temperature change in the body due to cells. The metabolic rate of cancer cells is high compared to normal cells. A high metabolic rate increases the blood flow in cancer cells. High blood leads to changes in body temperature. The change in body temperature is used for cancer cell detection at an earlier stage. However, T1-stage cancer cells are smaller and have small temperature differences undetected with thermography. In this paper, a T1-stage cancer cell is heated by an external source; then, thermal images are acquired for earlier detection of small-size cancer cells. External heat source amplifies T1 stage cancer cell temperature. Amplified cancer cell images are analyzed using the proposed Multiwavelet-Deep Denoised Convolutional Neural Network (MWTDnCNN) algorithm for T1 cancer cell detection. Amplified T1 stage cancer cell has higher thermal conductivity (k) and heat capacity (Cp), which helps to detect T1 cancer cell tissue due to the enhanced pixel feature. The proposed MWTDnCNN algorithm has a T1-stage cancer cell detection accuracy of about 98% compared with traditional algorithms. The proposed MWTDnCNN algorithm detects T1-stage cancer of size 1.29 mm.

Abstract Maintaining eye contact is a fundamental aspect of non-verbal communication, yet current remote communication tools, such as video calls, struggle to replicate the natural eye contact experienced in face-to-face interactions. This study presents a cutting-edge vision-sharing system for android avatars that enables remote eye contact by synchronizing the eye movements of the operator and the avatar. Our innovative system features an eyeball integrated with a wide-angle lens camera, meticulously designed to mimic human eyes in both appearance and functionality. This technology is seamlessly integrated into android avatars, enabling operators to perceive the avatar’s surroundings as if physically present. It provides a stable and immersive visual experience through a head-mounted display synchronized with the avatar’s gaze direction. Through rigorous experimental evaluations, we demonstrated the system’s ability to faithfully replicate the operator’s perspective through the avatar, making eye contact more intuitive and effortless compared with conventional methods. Subjective assessments further validated the system’s capacity to reduce operational workload and enhance user experience. These compelling findings underscore the potential of our vision-sharing system to elevate the realism and efficacy of remote communication using android avatars.

Abstract This article introduces an advanced nonlinear controller designed for optimizing the performance of a single‐link robot arm featuring a flexible joint. The proposed nonlinear control strategy incorporates a Proportional‐Integral (PI) controller in conjunction with a nonlinear velocity feedback component, aimed at providing effective nonlinear damping and suppressing vibrations. To validate the controller's performance, extensive simulations are conducted utilizing machine learning techniques within the Python environment. The performance of the proposed nonlinear damping controller is benchmarked against a conventional linear cascaded P‐PI control structure, with both controllers fine‐tuned using the Nelder‐Mead algorithm. Simulation results demonstrate that the nonlinear damping controller yields substantial improvements in the dynamic behavior of the robot axis arm, showcasing superior step and sinusoidal position tracking performance, along with active vibration damping capabilities. This research contributes valuable insights into the enhanced nonlinear control strategies for flexible‐joint robot arms, offering promising advancements in their overall dynamic performance.

Abstract This article considers the problem of output feedback stabilization for a class of stochastic high‐order nonlinear time‐delay systems with unknown output function. For stochastic high‐order nonlinear time‐delay systems, based on the Lyapunov stability theorem, by combining the addition of one power integrator and homogeneous domination method, the maximal open sector Δ of output function is given. As long as output function belongs to any closed sector included in Δ, an output feedback controller can be developed to guarantee the closed‐loop system globally asymptotically stable in probability.

Abstract Aiming at the problem of sub‐synchronous oscillations induced by direct‐drive wind farms with series‐compensated lines, this paper proposes an unknown system dynamics estimation‐based PI controller to achieve sub‐synchronous oscillation suppression. According to the mathematical model of the direct‐drive wind farm grid‐connected system, the relationship between the direct‐drive wind turbine grid‐side converter current inner‐loop PI controller and the sub‐synchronous components is first established. Secondly, the uncertain sub‐synchronous current components and voltage components in the series‐compensated lines of the direct‐drive wind farm are taken as the total disturbance, and an unknown system dynamic estimator‐based PI controller is designed by introducing the first‐order low‐pass filter operation. Then, the stability and convergence of the closed‐loop system are proved by Lyapunov theory. Finally, the Prony method is used to analyse the current signal output by the direct‐drive wind turbine, and the inherent characteristics of the negative damping of the SSO induced by the series‐compensated line of the direct‐driven wind farm are revealed. A comparative numerical simulation is carried out to demonstrate that the sub‐synchronous oscillations of the direct‐drive wind farm with series‐compensated lines can be suppressed under different operating conditions.

Abstract This paper presents the design of a complex‐step extended Kalman filter (CS‐EKF) to estimate the states of the twin‐rotor MIMO system (TRMS) which is a non‐linear system. Since the model of TRMS is quite complex and contains discontinuous functions, it is very difficult to calculate the Jacobian matrix in the TRMS analytically by hand. This makes it difficult to implement control methods that require Jacobian matrix calculation for TRMS. Herein, to calculate the Jacobian matrix, the CS‐EKF uses the complex‐step derivative approach, which is a numerical technique and offers near‐analytical accuracy in a single function evaluation. The effectiveness of the CS‐EKF is demonstrated through simulation and real‐time experiments. Also, The CS‐EKF is compared to the finite‐difference extended Kalman filter (FD‐EKF) and the unscented Kalman filter (UKF) in terms of estimation accuracy, computational load, and ease of implementation.

Abstract This paper proposes a novel finite‐time limit cycle controller for DC to AC conversion in power boost converters. The stable limit cycle is categorized as a positive limit set. Achieving the control law, based on the concepts of set stability and finite‐time stability, is a challenging problem. To fulfill the control objective, a novel sliding manifold is suggested concerning the structure of the wanted limit cycle which facilitates conditions for the development of finite‐time stability for the limit cycle. By utilizing the sliding mode control method, a control strategy is proposed that guarantees the desired stable limit cycle is created in the phase plane of the closed‐loop system and the phase trajectories reach it in a finite time and remain on it for all future times. This ensures the finite‐time generation of the biased sinusoidal oscillations in the output of the power boost converter from a DC input source. The simulation results of a practical boost converter have validated the effectiveness and feasibility of the presented algorithm.

Abstract The objective of this article is to present the implementation of a backstepping control regulator on a Xilinx Zedboard Zynq FPGA using the HDL Coder tool through the FPGA in‐the‐loop option, and to study its effectiveness when applied to a three‐dimensional robotic manipulator model. The analysis is based on the application of the backstepping control law for the three degrees of freedom PUMA 560 model, through the development of a dynamic simulation model. The results of practical implementation using the FPGA in the loop technique demonstrate the effectiveness of the proposed method using the Xilinx Zedboard Zynq FPGA, which provides a useful insight into the benefits of using backstepping control laws in robotics applications.

Abstract This work tackles the tracking control problem of robotic manipulators where the robot dynamics contains uncertain parameters and joint velocity measurements are not available. Specifically when the robotic manipulator is required to perform a periodic task repetitively, as in most industrial applications, a repetitive learning controller is proposed that does not require joint velocity measurements and can compensate the uncertainties of the robot dynamical parameters and additive disturbances caused due to the periodic joint motion. The proposed solution is achieved via the use of a novel learning component in the controller design in conjunction with a novel model‐free joint velocity observer design. The stability of the closed‐loop system and the convergence of both the joint position tracking error and the joint velocity observation error to the origin are guaranteed via Lyapunov based arguments. Experimental results performed on a 2 degree of freedom robot manipulator are presented to demonstrate the performance of the proposed observer–controller couple.

Abstract A new dual‐motor servo steering system with improved reliability and safety is proposed. But, despite the advantages of the proposed servo system, it is strongly coupled, non‐linear and multivariable, where the biggest challenge lies in its tracking and synchronization control. To improve the tracking and synchronization control performance of the proposed servo system, a tracking and synchronization control strategy based on backstepping super‐twisting control and multi‐level differential coupling is presented. First, a parallel model of the dual‐motor is established. Then, backstepping and super‐twisting control algorithms are integrated while adaptively optimizing key parameters to ensure the robustness and tracking performance of each motor. After that, an angular synchronization controller with multi‐level differential coupling and backstepping super‐twisting algorithm is proposed to compensate for the synchronization error of the dual‐motor system caused by parameter uncertainty. Finally, the simulation is carried out using Simulink to verify the effectiveness of the proposed control strategy.

Abstract This study investigates a novel tracking control with prescribed performance for an uncertain nonlinear 2‐DOF helicopter subject to actuator failure. The control design aims to address partial actuator faults, and to mitigate their effects, an adaptive auxiliary variable is introduced. Additionally, a neural network is employed to accurately approximate the system uncertainties. The prescribed performance is formulated as time‐varying constraints, and the barrier Lyapunov function (BLF) technique is applied to achieve the constrained control. Finally, the stability analysis of the closed‐loop system is provided, and the validity of the proposed control scheme is illustrated through a simulation study on the 2‐DOF helicopter system.

Abstract In this study, task space tracking control of robot manipulators driven by brushless DC (BLDC) motors is considered. Dynamics of actuators are taken into account and the entire electromechanical system (i.e. kinematic, dynamic, and electrical models) is assumed to include parametric/structured uncertainties. A novel adaptive controller is designed and the stability of the closed loop system is ensured via novel Lyapunov type tools. To demonstrate performance and applicability of the proposed method, a simulation study is conducted using the model of a two degree of freedom, planar robotic manipulator driven by BLDC motors.

Abstract The complexity of neuronal networks, characterized by interconnected neurons, presents significant challenges in control due to their nonlinear and intricate behaviour. This paper introduces a novel method designed to generate control inputs for neuronal networks to regulate the firing patterns of modules within the network. This methodology is built upon temporal deep unfolding‐based model predictive control, a technique rooted in the deep unfolding method commonly used in wireless signal processing. To address the unique dynamics of neurons, such as zero gradients in firing times, the method employs approximations of input currents using a sigmoid function during its development. The effectiveness of this approach is validated through extensive numerical simulations. Furthermore, control experiments were conducted by reducing the number of input neurons to identify critical features for control. Various selection techniques were utilized to pinpoint key input neurons. These experiments shed light on the importance of specific input neurons in controlling module firing within neuronal networks. Thus, this study presents a tailored methodology for managing networked neurons, extends temporal deep unfolding‐based model predictive control to nonlinear systems with reset dynamics, and demonstrates its ability to achieve desired firing patterns in neuronal networks.

As the world becomes increasingly digital, healthcare is no exception. With the ease of sharing e-healthcare records over open networks, smart healthcare systems have become a popular way to manage patient information. But as the popularity of these systems has grown, so has the concern for their security. That's where image security techniques come in. In this paper we have developed a new approach to secure e-patient records like DICOM images. By combining the redundant discrete wavelets transform (RDWT), Hessenberg Decomposition (HD), and randomized singular value decomposition (RSVD). We developed a robust and dual watermarking scheme. This scheme uses multiple watermarks, including Electronic Patient Record (EPR) as text and images, to ensure high-level authentication. In order to attain a balance between imperceptibility and robustness, a PSO-based optimization of scale factor is employed and Turbo code is utilized to encode the EPR and minimize channel noise. Additionally, the marked image undergoes encryption using a 3D chaotic-based encryption technique, and the extracted watermark is denoised through a deep neural network. The result shows that the proposed scheme is both secure and reliable. With this dual watermarking scheme, we have made great strides in securing e-patient records.

This paper proposes a novel approach that leverages a hybrid deep learning framework called the Squirrel Search-optimized Attention-Deep Recurrent Neural Network (SS-ADRNN) to optimize the management of charging stations, ensuring efficient resource allocation while safeguarding user data and minimizing operational costs. The SS-ADRNN model incorporates squirrel search optimization, which is inspired by the foraging behaviour of squirrels, to dynamically adjust charging station operations based on environmental conditions and demand patterns. Additionally, attention mechanisms are employed to prioritize relevant input features, enabling the model to focus on critical information during decision-making processes. Deep recurrent neural networks (RNNs) are utilized to capture temporal dependencies in charging station data, allowing for more accurate predictions and adaptive control strategies. Experimental evaluations demonstrate the effectiveness and feasibility of the proposed SS-ADRNN-based approach in real-world scenarios. The results showcase significant improvements in the detection of malicious traffic and cost minimization compared to traditional charging station management methods. Overall, this research contributes to advancing the field of intelligent charging station optimization, offering a robust and adaptable solution for EV and UAV charging infrastructures that prioritize both security and operational efficiency.

Contrast enhancement aims to amplify the visual quality of images by modifying the contrast level because digital images may get distorted by casual acquisition. The article deals with contrast enhancement as an optimization problem and uses the Dragonfly Algorithm (DA) to find the optimal grey-level intensity values. The DA for contrast enhancement uses five control parameters (entropy, number of edges, total intensities of edges, the variance of the probability of occurrence of each grey value, and the number of grey levels) to generate an objective function. An ablation study is also performed to understand how different controlling parameter combinations contribute to determining the optimal solution. The proposed approach considers 24 grey-scale images from the Kodak dataset and metrics as Peak Signal-to-Noise Ratio (PSNR), Visual Information Fidelity (VIF), and Structural Similarity Index Measure (SSIM) to verify the output's performance. The PSNR, VIF, and SSIM values in the experiments are 30.87, 0.7451, and 0.9523, respectively. The experimental observations reveal that the proposed DA-based image contrast enhancement produces high-quality images from its low-contrast counterparts. Comparisons with state-of-art methods ensure the superiority of the proposed algorithm. The Python implementation of the proposed approach is available in this Github repository.

The creation of high-performing concrete (HPC) is greatly influenced by the selection of materials, with cost and sustainability factors playing a bigger part in contemporary building techniques. To overcome these limitations, we developed a Multi-Objective Ant Colony Adaptive Dense Convolutional Neural Network (MOAC-ADenseNet) with 5-K-Fold cross validation, a dependable and precise forecasting model for the cost-effective selection of HPC material. First, we collect a concrete material dataset for evaluating the suggested method. MOAC-ADenseNet utilized Dense convolutional neural networks and ant colony optimization for complex material data analysis, which makes it easier to choose expensive and sustainable materials for high-performance concrete manufacturing operations. The experimental findings of the suggested approach are evaluated for the relative measure such as Pearson's Linear Correlation Coefficient (R) is 0.93, the Root Mean Square Error (RMSE) is 91.38, Mean Absolute Error (MAE) of 58.15, and Mean Absolute Percentage Error (MAPE) is 8.79. The outcomes demonstrated that the material cost of HPC was correctly predicted by the MOAC-ADenseNet. The actual measured value and the MOAC-ADenseNet model predictions, following 5-K-fold cross-validation and input feature improvement, shows its effectiveness. A The MOAC-ADenseNet approach provides feasible method for enhancing material selection in HPC manufacturing accomplishing sustainability and cost-effectiveness goals.

The effect of the void shape on cut blasting is investigated by establishing a damage analysis model for a void using an improved calculation formula for stress on the wall of the void. Additionally, an optimization scheme is provided for the “square void cutting theoretical model.” The vibration effect of the rock mass outside the excavation area is simultaneously monitored, and its validity is substantiated through experimental and simulation-based verification. The findings indicate that the variation of q2sinθ over time aligns with the dynamic loading process of wall stress in holes. Under the influence of longitudinal waves, thin-walled circular damage occurs, and tensile effects from reflected waves are influenced by impedance. In a square void cutting model, two-stage stress waves cause tensile shear damage and inward collapse in the rock mass along hole walls. The explosive energy generated by square holes significantly contributes to fragmentation of rock masses. The circular empty-hole cutting model generates significant vibrations in central areas due to resistance. Vibration velocity in 45° direction for circular holes is lower than that for square voids outside cuts while vibration velocity remains equivalent between circular and square holes at 90° direction.

As deepfake technology becomes increasingly sophisticated, the proliferation of manipulated images presents a significant threat to online integrity, requiring advanced detection and mitigation strategies. Addressing this critical challenge, our study introduces a pioneering approach that integrates Explainable AI (XAI) with Adversarial Robustness Training (ART) to enhance the detection and removal of deepfake content. The proposed methodology, termed XAI-ART, begins with the creation of a diverse dataset that includes both authentic and manipulated images, followed by comprehensive preprocessing and augmentation. We then employ Adversarial Robustness Training to fortify the deep learning model against adversarial manipulations. By incorporating Explainable AI techniques, our approach not only improves detection accuracy but also provides transparency in model decision-making, offering clear insights into how deepfake content is identified. Our experimental results underscore the effectiveness of XAI-ART, with the model achieving an impressive accuracy of 97.5% in distinguishing between genuine and manipulated images. The recall rate of 96.8% indicates that our model effectively captures the majority of deepfake instances, while the F1-Score of 97.5% demonstrates a well-balanced performance in precision and recall. Importantly, the model maintains high robustness against adversarial attacks, with a minimal accuracy reduction to 96.7% under perturbations.

Some traditional cryptographic techniques, like the Secure Hash Algorithm (SHA-256 for hashing), Rivest-Shamir-Adleman (RSA/Elliptic Curve for signing) and Advanced Encryption Standard (AES for encryption), perform well on systems with good hardware memory and processing capabilities. However, these techniques engage in conflict to keep up with the world of sensor networks and embedded systems. Lightweight cryptography plays a major role in security constraints, especially in resource-limited devices such as RFID tags, smart cards, sensor nodes and IoT. This paper proposes a flexible hardware architecture of lightweight m-Crypton block cipher for high-speed resource-constrained applications. The proposed architecture enables a single architecture appropriate for the many encryptions' key sizes. Therefore, the proposed architecture changes the security level in resource-constrained applications by integrating several key sizes into a single design. Furthermore, this architecture outperformed the conventional block ciphers in terms of throughput-to-area ratio achieving a 10.37 throughput-to-area ratio better than other lightweight block ciphers. The proposed design can be used in high bandwidth applications, high-end RFID and IoT smart devices. Hence, the proposed design demonstrates that increasing the speed of cipher implementation results in more plaintext transformations into ciphertext. All results have been verified and simulated for several Xilinx design suite families.

Partial shading conditions (PSCs) may be unpredictable and difficult to forecast in large-scale solar photovoltaic (PV) systems. Potentially degrading the PV system's performance results from numerous peaks in the P–V curve caused by PSC. On the other hand, the PV system must be run at its maximum power point (GMPP) to maximize its efficiency. Swarm optimization strategies have been employed to detect the GMPP; however, these methods are associated with an unacceptable amount of time to reach convergence. In this research, an innovative grey wolf optimization, abbreviated as NGWO, is presented as a solution to overcome the shortcomings of the standard GWO method, which includes long conversion times, a rate of failure, and large oscillations in a steady-state condition. This paper seeks to address these issues and fill a gap in research by enhancing the GWO's performance in tracking GMPP. The original GWO is modified to incorporate the Cuckoo Search (CS) abandoned process to shorten the time it takes for effective adoption. Based on the simulation finding, the proposed IGWO method beats other algorithms in most circumstances, particularly regarding tracking time and efficiency, where the average tracking time is 0.19s, and the average efficiency is 99.86%.

This article presents an active fault detection kit, applicable to low voltage single-phase electrical installations, in the prospect of the Zero Energy Building concept, integrating on-site renewable energy generation and energy storage. This simple, flexible, self-powered and compact kit is capable of detecting faults, such as power theft (meter tampering), unintentional islanding and neutral conductor loss. Its operation is based on harmonic voltage injection, in series with the electrical installation, through a low-power H-bridge inverter and a current transformer, along with the corresponding harmonic current measurement, to estimate the impedance and effectively detect faulty conditions; the fast and robust Goertzel algorithm is utilized. Moreover, it features IoT communication capabilities, employing the ESP32 microcontroller, to exchange data and information with the installation meters. The functionality and effective fault detection of the proposed device are validated, through experimental tests on a custom-developed hardware prototype; IoT connectivity and data uploading are experimentally tested and verified, too. Finally, a sustainability assessment study is performed, using the Life Cycle Cost Analysis tool.

The design of converters is essential for the proper use of electrical energy. Half-bridge topology represents a suitable conversion scheme to implement a boost rectifier converter. Consequently, this article proposes the parameter optimization of a proportional-integral-derivative (with filter) controller for a half-bridge boost rectifier with a high power factor. Regarding the high simulation time for the converter, stochastic hill-climbing and simulated annealing algorithms are employed for the optimization process. The results display that the optimized controller allows suitable values for the power factor and output waveform. The controller parameters obtained through optimization algorithms result in a high power factor of 0.9934 when the half-bridge boost rectifier is operating at full load.

Skin cancer has become a serious disease which has the potential to scale up if it is not identified earlier. It is imperative to detect and give treatment to skin cancer promptly. Diagnosing skin cancer manually takes a lot of time and it is costly, and the probability of false diagnosis has increased due to the outstanding resemblances among various skin lesions. Enhancing the classification of multi-class lesions of skin needs the development of investigative systems which should be automated. Data augmentation with GANs and Adaptive Conditional Generative Adversarial Network strategies improves performance. The performance is tested using balanced and unbalanced datasets. Using a proper process of augmentation of data, the suggested system attains a 94% accuracy for the VGG16, 93% for the ResNet50 and 94.25% for ResNet101. The process of collaboration of all such methods improves accuracy further to 95%. In summary, the novelty of the work lies in its holistic approach to automated skin lesion classification, incorporating advanced deep learning models, novel data augmentation techniques and comprehensive performance evaluation on real-world datasets. These contributions collectively advance the field of computer-aided diagnosis for the detection of skin cancer and treatment.

This research paper proposes a hybrid fuzzy logic controller for achieving autonomous path navigation and obstacle avoidance through the use of the Social Spider Optimizer algorithm. The proposed controller employs kinematic modelling to determine the mobile robot’s path navigation and utilizes a fuzzy logic system for effective control. The Social Spider Optimizer algorithm optimizes the parameters of the fuzzy controller, while the FLC is responsible for obstacle avoidance. The effectiveness of the proposed controller has been analyzed, and a comparative study has been carried out with optimization techniques like particle swarm optimization (PSO) and cuckoo search optimization (CSO) controllers. The study aims to propose a hybrid fuzzy logic controller, that provides efficient navigation and obstacle avoidance for mobile robots. In a simulation, the starting point is considered as (0,0) and the destination point is set as Xk = 1.1 and Yk = 1.2. The performance of the proposed method is compared with FLC and methods like PSO and CSO. With the SSO-based FLC, the proposed mobile robot identifies the obstacle distance and travels towards the destination with smooth navigation. The results show the efficacy of the proposed controller in comparison to other controllers for mobile robots in terms of path navigation and obstacle avoidance.

The conversion system for wind energy has no restriction on the number of output phases. K numbers of output phases can be converted into standard grid-connected three-phase supply using a quasi-Z source direct matrix converter (QZSDMC). The obtained input supply may be five phases from the wind energy conversion system with continuously variable frequency as well as variable terminal voltages. Using the proposed QZSDMC converter with maximum constant boost current control modulation technique constant three-phase voltages as well as frequency can be maintained at the grid side. Additionally, the energy conversion system has high output voltage gain. The proposed converter as well as the modulation technique produces the maximum voltage transfer ratio of 1.05. The output voltage gain reached nearly 1.99 compared with the traditional power converters. The voltage THD and current THD are maintained within the acceptable limit of 5.3 and 3.6 respectively. The power factor have been maintained nearly unity throughout the all mode of operations. To stabilize the grid frequencies and grid voltages additional control blocks are used. This research article presents simulation results for the proposed QZSDMC converter with a maximum constant boost current control modulation technique. Also, the proposed scheme has been validated with suitable experimental results.

The paper describes the influence of the magnetizing inductance of the transformer on zero-voltage switching of the primary transistors in a soft-switching full-bridge dc-dc converter with a controlled rectifier and turn-off snubber. The optimized version of the transformer allows for achieving a full zero-voltage and zero-current turn-on of the primary transistors in a full-bridge soft-switching DC-DC converter. The analysis is verified by measurements on a laboratory model of the converter. The influence of undischarged output capacitances on the efficiency is measured as well. Also, the impact of the GaN transistors on the zero-voltage switching is discussed.

Accurate lung cancer classification in magnetic resonance imaging (MRI) remains challenging due to the difficulty in detecting cancerous patterns. In response, this study introduces an attention-based VGG19 neural network for enhanced classification performance. Leveraging the VGG19 architecture's deep learning capabilities, our model incorporates attention mechanisms to selectively emphasize salient features during training. The attention-based approach addresses the challenge of discerning subtle patterns indicative of malignancy, significantly improving classification accuracy. We train and evaluate the model on a diverse dataset, ensuring its capacity to generalize across various patient cases. The attention mechanism proves effective in prioritizing critical regions within MRI scans, enhancing sensitivity and specificity in lung cancer detection. Additionally, we employ gradient analysis to interpret the decision-making process, providing valuable insights into influential features. Results demonstrate the proposed model's superiority over baseline approaches, showcasing its efficacy in inaccurate lung cancer classification. The attention-based VGG19 neural network not only advances classification capabilities but also offers interpretability crucial for gaining trust in automated diagnostic systems. This research contributes a robust solution to a pressing medical imaging challenge, holding promise for practical implementation in clinical settings to support radiologists in timely and accurate lung cancer diagnosis.

The advancements made in Software-Defined Networking (SDN) technology seem quite promising, with potential wide application in managing and controlling the latest network infrastructures. SDN technology decouples the control plane from the data plane, enabling effective and flexible network management. However, this dynamic phenomenon brings new security challenges. With the increasing dynamism and programmable nature of networks, conventional security protocols may not sufficient to protect against advanced and sophisticated attacks. Although Intrusion Detection Systems (IDSs) have been extensively applied for identifying and preventing security threats in traditional network environments, IDS models designed specifically for traditional network requirements may not be adequate for SDN environments. These issues may stem from the static nature of conventional networks, contrasting with the dynamicity of advanced SDN networks, and the traditional IDS’s inability to adapt to the dynamic nature of SDN. To address these challenges, the current research proposes a novel Deep Hybrid IDS model to enhance network security in SDN environments and prevent attacks using Scapy. The proposed model detects signature-based attacks by integrating Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) for real-time simulated datasets, achieving an accuracy of 97.8%, which is comparatively better than existing models.

Brain Tumor Segmentation (BTS) and classification are important and growing research fields. Magnetic resonance imaging (MRI) is commonly used in the diagnosis of brain tumours owing to its low radiation exposure and high image quality. One of the current subjects in the field of medical imaging is how to quickly and precisely segment MRI scans of brain tumours. Unfortunately, most existing brain tumour segmentation algorithms use inadequate 2D picture segmentation methods and fail to capture the spatial correlation between features. In this study, we propose a segmentation model (SwinVNETR) Swin V-NetTRansformer-based architecture with a non-local block. This model was trained using the Brain Tumor Segmentation Challenge BraTS 2021 dataset. The Dice similarity coefficients for the enhanced tumour (ET), whole tumour (WT), and tumour core (TC) are 0.84, 0.91, and 0.87, respectively. By leveraging this methodology, we can segment brain tumours more accurately than ever before. In conclusion, we present the findings of our model through the application of the Grad-CAM methodology, an eXplainable Artificial Intelligence (XAI) technique utilized to elucidate the insights derived from the model, which helped in better understanding; doctors can better diagnose and treat patients with brain tumours.

For improving the dynamic management performance of construction cost, the dynamic control model of cost of construction based on fuzzy neural network is studied. Consider the effect of resource allocation, construction progress and construction quality on the cost of project in construction stage, and build the cost control index for the project in stage of construction. The fuzzy logic model is used in selecting the main cost related indicators from project cost control index system at the construction stage as input neurons of the BP NN, and the BP neural network is employed to output the results of prediction of cost at the construction stage. The project cost prediction results are set as the data basis for the dynamic control of the project cost, determine the most optimistic cost, the most probable cost and the most pessimistic cost of project cost in stage of construction through key chain method, and set buffers to realize dynamic control of project cost in stages of construction. The evaluation results prove that the developed method will be able to accurately predict the project cost in stages of construction, and the cost saved in the construction phase of the project is more than 300000 yuan.

Speech emotion recognition (SER) is attractive in several domains, such as automated translation, call centres, intelligent healthcare, and human–computer interaction. Deep learning models for emotion identification need considerable labelled data, which is only sometimes available in the SER industry. A database needs enough speech samples, good features, and a better classifier to identify emotions efficiently. This study uses data augmentation to enhance the amount of input voice samples and address the data shortage issue. The database capacity increases by adding white noise to the speech signals by data augmentation. In this work, the Mel-frequency Cepstral Coefficient (MFCC) and Mel-frequency Magnitude Coefficient (MFMC) features, along with a one-dimensional convolutional neural network (1D-CNN), are used to classify speech emotions. The datasets utilized to estimate the model's enactment were AESDD, CAFE, EmoDB, IEMOCAP, and MESD. The data augmentation with the 1D-CNN (MFMC) model performed best, with an average accuracy of 99.2% for AESDD, 99.5% for CAFE, 97.5% for EmoDB, 92.4% for IEMOCAP and 96.9% for the MESD database. The proposed 1D-CNN (MFMC) with data augmentation outperforms the 1D-CNN (MFCC) without data augmentation in emotion recognition.

Abstract The present investigation aims to address the leader‐following consensus issue for variable‐order fractional multi‐agent systems (VOFMASs) under actuator faults and unknown external disturbances. The Caputo definition for the variable‐order fractional (VOF) derivative is used to model the non‐linear dynamics of the leader and follower agents. Consequently, two lemmas are developed for the Caputo VOF derivative of the Lyapunov function. In the first case, it is assumed that the multi‐agent system (MAS) operates without actuator faults and an adaptive controller is proposed. With the aid of the developed lemmas, assurance is provided for the finite‐time bounded cooperative tracking of the VOFMAS despite the presence of unknown external disturbances. In the second case, a novel fault‐tolerant controller is designed for the finite‐time consensus of the MAS under two common kinds of actuator faults: loss of effectiveness fault and bias fault. Finally, the efficacy of the proposed controller is demonstrated through the presentation of results from three simulation examples.

Abstract To address the stable grasping control issue in manipulator grasping systems, this manuscript proposes an improved multiverse optimizer‐based anti‐saturation model‐free adaptive control (IMVO‐AS‐MFAC) algorithm. Initially, the manuscript converts the manipulator grasping system into an equivalent data model through dynamic linearization techniques. Then, based on the dynamic linearization model, the IMVO‐AS‐MFAC controller is designed. To address the actuator saturation problem that commonly occurs during the clamping process of manipulator grasping systems, a saturation parameter is introduced into the IMVO‐AS‐MFAC algorithm. Meanwhile, the controller parameters are optimized using an improved multiverse optimizer algorithm, which involves modifications to the initial population distribution and location update strategy. The improved algorithm demonstrates more competitive optimization performance compared to the traditional multiverse optimizer. The major advantage of the IMVO‐AS‐MFAC algorithm lies in the fact that only the input and output data of the manipulator grasping system are required throughout the entire control process, and the controller parameters are derived using an optimization algorithm rather than relying on empirical knowledge. Furthermore, rigorous mathematical analysis confirms the stability of the IMVO‐AS‐MFAC approach, and its effectiveness is validated through semi‐physical experiments conducted in an environment integrating the MATLAB/Simulink module and the RecurDyn platform.

Abstract This paper proposes an improved two‐degree‐of‐freedom active disturbance rejection controller for the coupling problem of asynchronous motor vector system. To simplify the analysis process and accommodate observers of different types, a unified expression based on different controllers for the system output is developed. The closed‐loop transfer function generated by the reference input and load disturbance is given. For the coupling problem of motor output speed and immunity, the structure of a higher‐order extended state observer is reconstructed. The extended state observer estimates both the output speed and the total system disturbance, which serve as feedback and feed‐forward compensation quantities. Compared to the PI controller and traditional active disturbance rejection controller, the proposed controller achieves decoupling of output response speed and immunity, simplifies the process of parameter tuning. Finally, simulation and experiment results verify the feasibility and effectiveness of the algorithm in this paper.

Abstract This article presents a novel approach for adaptive nonlinear state estimation in a modified autoregressive time series with fixed coefficients, leveraging an adaptive polynomial Kalman filter (APKF). The proposed APKF dynamically adjusts the evolving system dynamics by selecting an appropriate autoregressive time‐series model corresponding to the optimal polynomial order, based on the minimum residual error. This dynamic selection enhances the robustness of the state estimation process, ensuring accurate predictions, even in the presence of varying system complexities and noise. The proposed methodology involves predicting the next state using polynomial extrapolation. Extensive simulations were conducted to validate the performance of the APKF, demonstrating its superiority in accurately estimating the true system state compared with traditional Kalman filtering methods. The root‐mean‐square error was evaluated for various combinations of standard deviations of sensor noise and process noise for different sample sizes. On average, the root‐mean‐square error value, which represents the disparity between the true sensor reading and estimate derived from the adaptive Kalman filter, was 35.31% more accurate than that of the traditional Kalman filter. The comparative analysis highlights the efficacy of the APKF, showing significant improvements in state estimation accuracy and noise resilience.

Abstract This article presents a reachability‐based receding horizon control (RHC) method for addressing persistent monitoring problems with count requirements. An agent is assigned to monitor multiple targets in a given environment to minimize the average uncertainty metric of all targets, while ensuring the monitoring count requirements of specific targets within predetermined time windows. To account for the spatial and temporal constraints in the monitoring requirements, a persistence predicate within the signal temporal logic (STL) specifications is introduced, which incorporates cumulative target state signals to effectively describe the monitoring count constraints. Considering the complexities arising from global time domain information requirements in STL constraints validation, an STL formula segmentation method based on completion progress is proposed. Subsequently, a reachability‐based controller for the agent is developed by solving a short‐term RHC problem while ensuring the satisfaction of the STL formulae. Simulation results are provided to illustrate the performance of proposed method.

Abstract A data‐driven Buck converter model identification method is proposed to deal with missing (incomplete) outputs, which is robust to the data length and percentage of missing data. A nuclear norm based convex optimization problem instead of linear interpolation, to guarantee the recovered missing data satisfying the potential model structured low‐rank character, is constructed to estimate missing outputs. The alternating direction method of multiplier strategy is used to solve the nuclear norm based convex optimization problem. In this way, the high‐quality missing data can be estimated, even for short data length and high percentage of missing data. Based on the recovered data, the subspace identification method provides accurate estimates of the structure and parameter of the Buck converter synchronously. By applying the proposed method to a Buck converter, experimental results demonstrate its effectiveness.

Abstract This paper concentrates on synthesizing robust predictive controllers in uncertain models with time‐delay and saturated input. To handle the complexities simultaneously and reach the desired objective, a state‐feedback structure with unknown gains is considered the compensator. Then, to specify the instantaneous values of the regulator's gains, an optimization issue will be derived relying on linear matrix inequality. Accordingly, in uncertain continuous‐time systems with some constraints and time‐delays, the controller's coefficients would be found in an online way from such an optimization. Numerous continuous‐time simulations are numerically performed to reveal the merit and robustness of the suggested methodology over similar techniques.

Abstract This paper investigates the control problem of spacecraft rendezvous with obstacle constraint, considering the external disturbance forces caused by orbit perturbation. Firstly, the translational dynamic model of spacecraft rendezvous is given and then rewritten into a second‐order fully‐actuated system form. Then, by employing the prescribed performance control method, the performance function and error transformation are determined, pre‐defining the prescribed performance bounds. Moreover, the fully‐actuated system approach is used to linearize the original nonlinear system, which simplifies the processes of control law design and ensures model accuracy. After that, to ensure that the spacecraft could avoid the dangerous zone during its manoeuvre, the artificial potential function is introduced, based on which a sliding mode surface is designed. Finally, the prescribed performance control–artificial potential function‐based control law is derived, further adopting the neuro‐adaptive method to deal with external interferences. The stability of the close‐loop control system is analysed through the Lyapunov approach and the effectiveness of the proposed control scheme is verified by carrying out a numerical simulation.

Abstract This study focuses on the highway platoon driving mode and proposes a distributed adaptive control algorithm based on an observer. Firstly, the adaptive observer is designed to compensate for the effect of unknown driving resistance and thus enhance the adaptation ability of the system to uncertainty. Secondly, an auxiliary system is introduced to specifically address actuator saturation constraints, ensuring the stability of the platoon driving in extreme conditions. Lastly, combining an event‐triggered mechanism, a control strategy is designed to achieve the stability of the entire platoon while maximizing the conservation of communication resources. The algorithm's viability and efficiency are confirmed through simulation outcomes.

Abstract This paper explores the application of computer vision and mathematical modeling to analyze the intricate movements involved in weaving a traditional farming tool, the winnowing basket. By utilizing OpenPose algorithms, the study simplifies and visualizes the craftsmen's motions, particularly focusing on wrist movements. Video data of craftsmen in Chiba, Japan, creating Kizumi (place name) winnowing baskets is used as the basis for analysis. The extracted information is used to generate 2D motion trajectories of the wrist, allowing a comparison between beginners who watched parsed videos and those who watched the original videos in terms of skill acquisition and learning time. By visualizing human body behavior and combining statistical results, this study demonstrates the potential of artificial intelligence techniques such as computer vision for observing repetitive human movement and inheriting traditional skills.

Abstract Polymerase chain reaction (PCR) is an effective method for diagnosing infectious diseases and has been the primary method throughout the novel coronavirus disease (COVID-19) pandemic. PCR tests (from specimen collection to result acquisition) involve sample pretreatment, nucleic acid extraction, and PCR procedure. Automating the pretreatment process is crucial to mitigate the risk of infection for workers and to reduce the likelihood of sample contamination-triggered misdiagnosis, particularly when handling centrifuge tubes, cryopreservation tubes, and microtubes. Robotic systems have been engineered to automate cell culture and PCR-based diagnosis, predominantly designed for use with screw-capped containers. However, this leaves a notable gap in automation solutions for microtubes equipped with press-type caps. To address this gap, we developed a versatile microtube capper/decapper system. On the other hand, many tasks of manual operation using microtubes, which are routinely conducted in clinical tests and biological experiments, are performed. Compared to screw-type caps for centrifuge and cryopreservation tubes, press-type caps for microtubes present a considerably higher risk of the worker's fingers contacting the inside of the cap and/or generating airborne droplets. Despite the risks of contamination and infection derived from the manual handling of microtube caps, which can compromise diagnosis/experiment accuracy and worker safety, devices for manually opening and closing microtube caps without direct contact remain lacking. Therefore, leveraging the technology from the developed versatile microtube capper/decapper system for laboratory automation, we created a manually operated microtube equipped with an automatic capper/decapper system tailored for personnel in clinical and biological laboratories. In this study, we first examined the required specifications and prerequisites for a manual microtube capper/decapper and clarified the operating methods, operating procedures, operation environment, device size, accompanying functions, etc. Based on the required specifications and preconditions, we proceeded with the mechanical and control design of the conceptual model, manufactured a prototype, and confirmed its basic functions and performance. The compliant to the required specifications and preconditions and the usefulness of the proposed manual microtube capper/decapper were validated through various experiments and demonstrations. Using the proposed microtube capper/decapper, even small-scale operations, which are challenging to streamline, can be performed nearly as efficiently as full manual operations. Although operation time was not reduced, the ability to open and close microtubes without manual contact is crucial for improving diagnostic and experimental accuracy and for reducing the burden on and enhancing the safety of laboratory personnel. Because microtubes are used in various clinical tests and biological experiments, we believe that the proposed system can markedly reduce the workload for personnel across numerous clinical and biological laboratories.

Abstract This study aimed to develop daily living support robots for patients with hemiplegia and the elderly. To support the daily living activities using robots in ordinary households without imposing physical and mental burdens on users, the system must detect the actions of the user and move appropriately according to their motions. We propose a reaching-position prediction scheme that targets the motion of lifting the upper arm, which is burdensome for patients with hemiplegia and the elderly in daily living activities. For this motion, it is difficult to obtain effective features to create a prediction model in environments where large-scale sensor system installation is not feasible and the motion time is short. We performed motion-collection experiments, revealed the features of the target motion and built a prediction model using the multimodal motion features and deep learning. The proposed model achieved an accuracy of 93% macro average and F1-score of 0.69 for a 9-class classification prediction at 35% of the motion completion.

Abstract The manipulation of deformable linear objects (DLOs) such as ropes, cables, and hoses by robots has promising applications in various fields such as product assembly and surgical suturing. However, DLOs are more difficult to manipulate than rigid objects because their shape changes during manipulation. Furthermore, preventing a DLO from colliding with the environment is important to prevent it from becoming entangled and causing shape control to fail. In this paper, we proposed an obstacle avoidance and shape control scheme for DLOs based on differentiable simulation that does not require prior data or a specialized controller. First, we established a dynamic model of the DLO that allows for both forward dynamics transfer and error backpropagation to obtain gradients. Then, we employed model predictive control to optimize the embedded neural network for predicting the actions that would manipulate the DLO. Finally, the control scheme was made applicable to DLOs with different material properties by allowing online adaptation of the model parameters essential to deformation during manipulation. Simulations and real-world experiments demonstrate that the proposed control scheme could manipulate the DLO stably and accurately to avoid obstacles and achieve the goal state. In addition, the online adaptation of parameters helped mitigate the sim-to-real gap.

Abstract This paper describes a measuring unit for synchronously collecting the air dose rate and measurement position for efficient dosimetry surveying and data logging. The developed prototype comprises a three-dimensional light detection and ranging-based mapping part and dosimetry part, which are integrated into a single measuring unit through an embedded computer that installs a ROS (robot operating system) framework. The unit can function as a standalone system with embedded batteries. Since it is portable, on-line data gathering in the workspace can be realized, thereby maintaining consistency between the air dose rate and measurement position. In this paper, we describe the functional requirements for the measuring unit, the prototype system configuration, and the experimental results obtained in the mockup environment and nuclear facility to discuss its performance.

Abstract A new payoff function is proposed for cancer treatment optimisation, the tumour elimination payoff (TEP), that incorporates the increase in lifespan if tumour elimination is achieved. The TEP is discounted by drug toxicity and by potential risks, such as metastasis and mutation. An approximation is used for the probability of tumour elimination, e−αN(T), giving a terminal payoff with an exponential dependence on the final tumour size N(T). The optimal solutions for this payoff for simple tumour growth models, (logistic and Gompertz growth), are determined. Using Pontryagin's maximum principle it is proved that bang–bang optimal solutions exist with a single switch; specifically delayed treatment and treat‐and‐stop solutions at maximum tolerated dose (MTD) exist. There is also a singular arc with constant tumour size. Solutions either have a high probability, respectively, low probability of tumour elimination; these correspond to a post‐treatment high probability of cure, and a high probability of relapse, respectively. Optimising over the time horizon T results in solutions that are either MTD throughout or no treatment, that is, treatment is either beneficial or detrimental. For the logistic growth model, the treatment benefit phase diagram is derived with respect to the patient's expected increase in lifespan and tumour size.