Abubakar Elsafi^1,*, Arafat Abdulgader Mohammed Elhag², Lubna A. Gabralla³, Ali Ahmed⁴, Ashraf Osman Ibrahim⁵

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.1, pp. 621-647, 2025, DOI:10.32604/cmes.2025.072726 - 30 October 2025

Abstract Energy efficiency stands as an essential factor when implementing deep reinforcement learning (DRL) policies for robotic control systems. Standard algorithms, including Deep Deterministic Policy Gradient (DDPG), primarily optimize task rewards but at the cost of excessively high energy consumption, making them impractical for real-world robotic systems. To address this limitation, we propose Physics-Informed DDPG (PI-DDPG), which integrates physics-based energy penalties to develop energy-efficient yet high-performing control policies. The proposed method introduces adaptive physics-informed constraints through a dynamic weighting factor (), enabling policies that balance reward maximization with energy savings. Our motivation is to overcome the… More >

Huifang Yang^1,*, Peixuan Kuang²

Journal of Psychology in Africa, Vol.35, No.4, pp. 535-540, 2025, DOI:10.32604/jpa.2025.070124 - 17 August 2025

Abstract The study investigated the effects of monetary rewards and punishments on the behavioral inhibition in children with attention deficit hyperactivity disorder (ADHD) tendencies. The present study adopted the signal stopping task paradigm, with 66 children with ADHD tendencies as the research subjects. A mixed design of 2 (reward and punishment type: reward, punishment) × 2 (stimulus type: monetary stimulus, social stimulus) was used. The analysis applied a between intervention group (with reward and punishment type variables) and within type of reward approach (by stimulus type as intra subject variables). The results showed that monetary punishment More >

Jie He, Dongmei Zhao, Tao Liu^*, Qingfeng Zou, Jian’an Xie

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 2733-2749, 2025, DOI:10.32604/cmc.2025.065205 - 03 July 2025

Abstract Robot navigation in complex crowd service scenarios, such as medical logistics and commercial guidance, requires a dynamic balance between safety and efficiency, while the traditional fixed reward mechanism lacks environmental adaptability and struggles to adapt to the variability of crowd density and pedestrian motion patterns. This paper proposes a navigation method that integrates spatiotemporal risk field modeling and adaptive reward optimization, aiming to improve the robot’s decision-making ability in diverse crowd scenarios through dynamic risk assessment and nonlinear weight adjustment. We construct a spatiotemporal risk field model based on a Gaussian kernel function by combining… More >

Zhiyuan Zhang¹, Yongjun Wu¹, Xiqin Li¹, Minghui Song¹, Guangwu Zhang², Ziren Wang^3,*, Wei Li³

Energy Engineering, Vol.122, No.5, pp. 1919-1948, 2025, DOI:10.32604/ee.2025.063178 - 25 April 2025

Abstract The park-level integrated energy system (PIES) is essential for achieving carbon neutrality by managing multi-energy supply and demand while enhancing renewable energy integration. However, current carbon trading mechanisms lack sufficient incentives for emission reductions, and traditional optimization algorithms often face challenges with convergence and local optima in complex PIES scheduling. To address these issues, this paper introduces a low-carbon dispatch strategy that combines a reward-penalty tiered carbon trading model with P2G-CCS integration, hydrogen utilization, and the Secretary Bird Optimization Algorithm (SBOA). Key innovations include: (1) A dynamic reward-penalty carbon trading mechanism with coefficients (μ = 0.2,… 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 >

Emran Al-Buraihy, Dan Wang^*

CMC-Computers, Materials & Continua, Vol.79, No.3, pp. 3913-3938, 2024, DOI:10.32604/cmc.2024.048104 - 20 June 2024

Abstract Cross-lingual image description, the task of generating image captions in a target language from images and descriptions in a source language, is addressed in this study through a novel approach that combines neural network models and semantic matching techniques. Experiments conducted on the Flickr8k and AraImg2k benchmark datasets, featuring images and descriptions in English and Arabic, showcase remarkable performance improvements over state-of-the-art methods. Our model, equipped with the Image & Cross-Language Semantic Matching module and the Target Language Domain Evaluation module, significantly enhances the semantic relevance of generated image descriptions. For English-to-Arabic and Arabic-to-English cross-language… More >

Yan Li, Qiyuan Wang^*, Kaidi Jia

CMC-Computers, Materials & Continua, Vol.78, No.2, pp. 2469-2489, 2024, DOI:10.32604/cmc.2024.047822 - 27 February 2024

Abstract Image description task is the intersection of computer vision and natural language processing, and it has important prospects, including helping computers understand images and obtaining information for the visually impaired. This study presents an innovative approach employing deep reinforcement learning to enhance the accuracy of natural language descriptions of images. Our method focuses on refining the reward function in deep reinforcement learning, facilitating the generation of precise descriptions by aligning visual and textual features more closely. Our approach comprises three key architectures. Firstly, it utilizes Residual Network 101 (ResNet-101) and Faster Region-based Convolutional Neural Network… More >

Shun Ma¹, Na Yu¹, Xiuna Wang², Shiyan Mei¹, Mingrui Zhao^2,*, Xiaoyu Han²

Energy Engineering, Vol.120, No.10, pp. 2369-2392, 2023, DOI:10.32604/ee.2023.028727 - 28 September 2023

Abstract Using the improved prospect theory with the linear transformations of rewarding good and punishing bad (RGPBIT), a new investment ranking model for power grid construction projects (PGCPs) is proposed. Given the uncertainty of each index value under the market environment, fuzzy numbers are used to describe qualitative indicators and interval numbers are used to describe quantitative ones. Taking into account decision-maker’s subjective risk attitudes, a multi-criteria decision-making (MCDM) method based on improved prospect theory is proposed. First, the [−1, 1] RGPBIT operator is proposed to normalize the original data, to obtain the best and worst More >

Anubha¹, Ravneet Preet Singh Bedi², Arfat Ahmad Khan^3,*, Mohd Anul Haq⁴, Ahmad Alhussen⁵, Zamil S. Alzamil⁴

CMC-Computers, Materials & Continua, Vol.75, No.1, pp. 1331-1351, 2023, DOI:10.32604/cmc.2023.033181 - 06 February 2023

Abstract Mobile adhoc networks have grown in prominence in recent years, and they are now utilized in a broader range of applications. The main challenges are related to routing techniques that are generally employed in them. Mobile Adhoc system management, on the other hand, requires further testing and improvements in terms of security. Traditional routing protocols, such as Adhoc On-Demand Distance Vector (AODV) and Dynamic Source Routing (DSR), employ the hop count to calculate the distance between two nodes. The main aim of this research work is to determine the optimum method for sending packets while… More >

Tingshun Li¹, Jiaohui Xu^1,*, Zesan Liu², Dadi Wang², Wen Tan¹

CMES-Computer Modeling in Engineering & Sciences, Vol.134, No.2, pp. 767-782, 2023, DOI:10.32604/cmes.2022.020702 - 31 August 2022

Abstract The blades of wind turbines located at high latitudes are often covered with ice in late autumn and winter, where this affects their capacity for power generation as well as their safety. Accurately identifying the icing of the blades of wind turbines in remote areas is thus important, and a general model is needed to this end. This paper proposes a universal model based on a Deep Neural Network (DNN) that uses data from the Supervisory Control and Data Acquisition (SCADA) system. Two datasets from SCADA are first preprocessed through undersampling, that is, they are… More >