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 >

Shahid Sultan¹, Qaisar Javaid¹, Eid Rehman^2,*, Ahmad Aziz Alahmadi³, Nasim Ullah³, Wakeel Khan⁴

CMC-Computers, Materials & Continua, Vol.70, No.3, pp. 6089-6106, 2022, DOI:10.32604/cmc.2022.021374 - 11 October 2021

Abstract For efficient and robust information exchange in the vehicular ad-hoc network, a secure and trusted incentive reward is needed to avoid and reduce the intensity of misbehaving nodes and congestion especially in the case where the periodic beacons exploit the channel. In addition, we cannot be sure that all vehicular nodes eagerly share their communication assets to the system for message dissemination without any rewards. Unfortunately, there may be some misbehaving nodes and due to their selfish and greedy approach, these nodes may not help others on the network. To deal with this challenge, trust-based… More >

Wadhah Zeyad Tareq^*, Mehmet Fatih Amasyali

CMC-Computers, Materials & Continua, Vol.70, No.2, pp. 2401-2414, 2022, DOI:10.32604/cmc.2022.020036 - 27 September 2021

Abstract The main idea of reinforcement learning is evaluating the chosen action depending on the current reward. According to this concept, many algorithms achieved proper performance on classic Atari 2600 games. The main challenge is when the reward is sparse or missing. Such environments are complex exploration environments like Montezuma’s Revenge, Pitfall, and Private Eye games. Approaches built to deal with such challenges were very demanding. This work introduced a different reward system that enables the simple classical algorithm to learn fast and achieve high performance in hard exploration environments. Moreover, we added some simple enhancements… More >

Iftikhar Ahmad^1,*, Abdulwahab Ali Almazroi², Mohammed A. Alqarni³, Muhammad Kashif Nawaz¹

Intelligent Automation & Soft Computing, Vol.31, No.2, pp. 1131-1142, 2022, DOI:10.32604/iasc.2022.020715 - 22 September 2021

Abstract In a classical k-min search problem, an online player wants to buy k units of an asset with the objective of minimizing the total buying cost. The problem setting allows the online player to view only a single price quotation at each time step. A price quotation is the price of one unit of an asset. After receiving the price quotation, the online player has to decide on the number of units to buy. The objective of the online player is to buy the required k units in a fixed length investment horizon. Online algorithms are proposed More >

Bing Wang^1,2, Kailei Deng¹, Liting He¹, Zhenming Sun^1,*

Energy Engineering, Vol.118, No.5, pp. 1333-1351, 2021, DOI:10.32604/EE.2021.014258 - 16 July 2021

Abstract China has implemented both quantitative and policy incentives for renewable energy development since 2019 and is currently in the policy transition stage. The implementation of renewable portfolio standards (RPSs) is difficult due to the interests of multiple stakeholders, including power generation enterprises, power grid companies, power users, local governments, and the central government. Based on China’s RPS policy and power system reform documents, this research sorted out the core game decision problems of China’s renewable energy industry and established a conceptual game decision model of the renewable energy industry from the perspective of local governments,… More >