Hira Akhtar Butt¹, Khoula Said Al Harthy², Mumtaz Ali Shah³, Mudassar Hussain^2,*, Rashid Amin^4,*, Mujeeb Ur Rehman¹

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 3003-3031, 2024, DOI:10.32604/cmc.2024.057185 - 18 November 2024

Abstract Detecting sophisticated cyberattacks, mainly Distributed Denial of Service (DDoS) attacks, with unexpected patterns remains challenging in modern networks. Traditional detection systems often struggle to mitigate such attacks in conventional and software-defined networking (SDN) environments. While Machine Learning (ML) models can distinguish between benign and malicious traffic, their limited feature scope hinders the detection of new zero-day or low-rate DDoS attacks requiring frequent retraining. In this paper, we propose a novel DDoS detection framework that combines Machine Learning (ML) and Ensemble Learning (EL) techniques to improve DDoS attack detection and mitigation in SDN environments. Our model… More >

Yameng Yin¹, Lieping Zhang^2,*, Xiaoxu Shi¹, Yilin Wang³, Jiansheng Peng⁴, Jianchu Zou⁴

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2769-2790, 2024, DOI:10.32604/cmc.2024.056791 - 18 November 2024

Abstract By integrating deep neural networks with reinforcement learning, the Double Deep Q Network (DDQN) algorithm overcomes the limitations of Q-learning in handling continuous spaces and is widely applied in the path planning of mobile robots. However, the traditional DDQN algorithm suffers from sparse rewards and inefficient utilization of high-quality data. Targeting those problems, an improved DDQN algorithm based on average Q-value estimation and reward redistribution was proposed. First, to enhance the precision of the target Q-value, the average of multiple previously learned Q-values from the target Q network is used to replace the single Q-value… More >

Van-Truong Nguyen^1,*, Dai-Nhan Duong¹, Dinh-Hieu Phan¹, Thanh-Lam Bui¹, Xiem HoangVan², Phan Xuan Tan³

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2337-2356, 2024, DOI:10.32604/cmc.2024.055412 - 18 November 2024

Abstract This paper proposes an adaptive nonlinear proportional-derivative (ANPD) controller for a two-wheeled self-balancing robot (TWSB) modeled by the Lagrange equation with external forces. The proposed control scheme is designed based on the combination of a nonlinear proportional-derivative (NPD) controller and a genetic algorithm, in which the proportional-derivative (PD) parameters are updated online based on the tracking error and the preset error threshold. In addition, the genetic algorithm is employed to adaptively select initial controller parameters, contributing to system stability and improved control accuracy. The proposed controller is basic in design yet simple to implement. The… More >

Shaowu Tang¹, Sicong Liu^1,*, Jian S Dai^1,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.30, No.3, pp. 1-1, 2024, DOI:10.32604/icces.2024.011746

Abstract Origami, a traditional and elegant folding technique, provides a solution for the deformation of three-dimensional structures. Inspired by this, origami-based soft actuators and robots exhibit the advantages of portability, high efficiency, and programmability when performing functions such as locomotion, manipulation, and interaction. However, these deformable origami structures bring challenges to sensing methods and technologies, due to hyperelastic deformations of the soft materials. In this work, a sensing approach is proposed to enable origami robots with proprioceptive and interactive sensing capabilities. The 3D-printed Miura-ori chambers of the robot are embedded with infrared optical sensors (a light-emitting… More >

Shen Su^1,*, Daojing He², Neeraj Kumar³

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.3, pp. 1933-1937, 2024, DOI:10.32604/cmes.2024.059318 - 31 October 2024

Abstract This article has no abstract. More >

Laviza Falak Naz¹, Rohail Qamar^2,*, Raheela Asif¹, Muhammad Imran², Saad Ahmed³

Intelligent Automation & Soft Computing, Vol.39, No.5, pp. 855-887, 2024, DOI:10.32604/iasc.2024.055074 - 31 October 2024

Abstract Domain shift is when the data used in training does not match the ones it will be applied to later on under similar conditions. Domain shift will reduce accuracy in results. To prevent this, domain adaptation is done, which adapts the pre-trained model to the target domain. In real scenarios, the availability of labels for target data is rare thus resulting in unsupervised domain adaptation. Herein, we propose an innovative approach where source-free domain adaptation models and Generative Adversarial Networks (GANs) are integrated to improve the performance of computer vision or robotic vision-based systems in… More >

Liang Yang^1,2, Jie Zhang¹, Jinfeng Xia¹, Siwen Zhang¹, Yang Yang³, Zhigang Chu^2,*

Sound & Vibration, Vol.58, pp. 171-183, 2024, DOI:10.32604/sv.2024.056968 - 21 October 2024

Abstract Helmholtz resonators are widely used to control low frequency noise propagating in pipes. In this paper, the elastic bottom plate of Helmholtz resonator is simplified as a single degree of freedom (SDOF) vibration system with acoustic excitation, and a one-dimensional lumped-parameter analytical model was developed to accurately characterize the structure-acoustic coupling and sound transmission loss (STL) of a Helmholtz resonator with an elastic bottom plate. The effect of dynamical parameters of elastic bottom plate on STL is analyzed by utilizing the model. A design criterion to circumvent the effect of wall elasticity of Helmholtz resonators More >

Juanling Liang¹, Wenguang Luo^1,2,*, Yongxin Qin¹

CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 1009-1027, 2024, DOI:10.32604/cmc.2024.055883 - 15 October 2024

Abstract An improved RRT* algorithm, referred to as the AGP-RRT* algorithm, is proposed to address the problems of poor directionality, long generated paths, and slow convergence speed in multi-axis robotic arm path planning. First, an adaptive biased probabilistic sampling strategy is adopted to dynamically adjust the target deviation threshold and optimize the selection of random sampling points and the direction of generating new nodes in order to reduce the search space and improve the search efficiency. Second, a gravitationally adjustable step size strategy is used to guide the search process and dynamically adjust the step-size to… More >

Mustafa Mohammed Alhassow^1,*, Oguz Ata², Dogu Cagdas Atilla¹

CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 749-771, 2024, DOI:10.32604/cmc.2024.055592 - 15 October 2024

Abstract This study investigates robot path planning for multiple agents, focusing on the critical requirement that agents can pursue concurrent pathways without collisions. Each agent is assigned a task within the environment to reach a designated destination. When the map or goal changes unexpectedly, particularly in dynamic and unknown environments, it can lead to potential failures or performance degradation in various ways. Additionally, priority inheritance plays a significant role in path planning and can impact performance. This study proposes a Conflict-Based Search (CBS) approach, introducing a unique hierarchical search mechanism for planning paths for multiple robots.… More >

Hoi Chuen Cheng, Frederick Ziyang Hong, Babar Hussain, Yiru Wang, Chik Patrick Yue^*

CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 161-181, 2024, DOI:10.32604/cmc.2024.053079 - 15 October 2024

Abstract Large-scale indoor 3D reconstruction with multiple robots faces challenges in core enabling technologies. This work contributes to a framework addressing localization, coordination, and vision processing for multi-agent reconstruction. A system architecture fusing visible light positioning, multi-agent path finding via reinforcement learning, and 360° camera techniques for 3D reconstruction is proposed. Our visible light positioning algorithm leverages existing lighting for centimeter-level localization without additional infrastructure. Meanwhile, a decentralized reinforcement learning approach is developed to solve the multi-agent path finding problem, with communications among agents optimized. Our 3D reconstruction pipeline utilizes equirectangular projection from 360° cameras to More >