Isaac Asare Boateng^1,2,*, Lord Amoah², Isogun Toluwalase Adewale³

Journal of Information Hiding and Privacy Protection, Vol.6, pp. 1-19, 2024, DOI:10.32604/jihpp.2024.051354 - 24 June 2024

Abstract Contrast enhancement in medical images has been vital since the prevalence of image representations in healthcare. In this research, the PRDHMCE (pairwise reversible data hiding for medical images with contrast enhancement) algorithm is proposed as an automatic contrast enhancement (CE) method for medical images based on region of interest (ROI) and non-region of interest (NROI). The PRDHMCE algorithm strategically enhances the ROI after segmentation using histogram stretching and data embedding. An initial histogram evaluation compares histogram bins with their neighbours to select the bin with the maximum pixel count. The selected bin is set as More >

Yosr Laatiri, Habib Sammouda, Fadhel Aloulou^*

Journal of Renewable Materials, Vol.12, No.4, pp. 771-798, 2024, DOI:10.32604/jrm.2024.047022 - 12 June 2024

Abstract This article aims to present the feasibility of storing thermal energy in buildings for solar water heating while maintaining the comfort environment for residential buildings. Our contribution is the creation of insulating composite panels made of bio-based phase change materials (bio-PCM is all from coconut oil), cement and renewable materials (treated wood fiber and organic clay). The inclusion of wood fibers improved the thermal properties; a simple 2% increase of wood fiber decreased the heat conductivity by approximately 23.42%. The issues of bio-PCM leakage in the cement mortar and a roughly 56.5% reduction in thermal… More > Graphic Abstract

Yue Cao^1,2, Longsheng Bao¹, Xiaowei Zhang^1,*, Zhanfei Wang¹, Bingqian Li¹

Structural Durability & Health Monitoring, Vol.18, No.4, pp. 485-503, 2024, DOI:10.32604/sdhm.2024.049698 - 05 June 2024

Abstract This study addresses the issue of inaccurate single damage fingerprint recognition during the process of bridge damage identification. To improve accuracy, the proposed approach involves fusing displacement mode difference and curvature mode difference data for single damage identification, and curvature mode difference and displacement mode wavelet coefficient difference data for two damage identification. The methodology begins by establishing a finite element model of the cable-stayed bridge and obtaining the original damage fingerprints, displacement modes, curvature modes, and wavelet coefficient differences of displacement modes through modal analysis. A fusion program based on the D-S evidence theory… More > Graphic Abstract

Hantao Huang, Zhifang Zhang^*, Zhenhua Wu, Yao Liu

Structural Durability & Health Monitoring, Vol.18, No.4, pp. 409-423, 2024, DOI:10.32604/sdhm.2024.048597 - 05 June 2024

Abstract In this paper, recycled carbon fiber reinforced polymer (CFRP) mixture (CFRP-M, including recycled carbon fiber and powder) and refined recycled CFRP fiber (CFRP-F, mostly recycled carbon fiber) were added to cement to study the influence of addition on the flexural strength, compressive strength, and fluidity of cement-based materials. The recycled CFRP were prepared by mechanically processing the prepreg scraps generated during the manufacture of CFRP products. For comparison, commercial carbon fiber powder was also added in cement and the performance was compared to that of addition of recycled CFRP. The hydration products and strengthening mechanism… More >

Guanfu Wang¹, Yudie Sun¹, Jinling Li^2,3,*, Yu Jiang¹, Chunhui Li¹, Huanan Yu^2,3, He Wang^2,3, Shiqiang Li^2,3

Energy Engineering, Vol.121, No.6, pp. 1671-1695, 2024, DOI:10.32604/ee.2024.047794 - 21 May 2024

Abstract Traditional optimal scheduling methods are limited to accurate physical models and parameter settings, which are difficult to adapt to the uncertainty of source and load, and there are problems such as the inability to make dynamic decisions continuously. This paper proposed a dynamic economic scheduling method for distribution networks based on deep reinforcement learning. Firstly, the economic scheduling model of the new energy distribution network is established considering the action characteristics of micro-gas turbines, and the dynamic scheduling model based on deep reinforcement learning is constructed for the new energy distribution network system with a More >

Fuju Zhou^*, Li Li, Tengfei Jia, Yongchang Yin, Aixiang Shi, Shengrong Xu

Energy Engineering, Vol.121, No.6, pp. 1697-1711, 2024, DOI:10.32604/ee.2024.047680 - 21 May 2024

Abstract When a line failure occurs in a power grid, a load transfer is implemented to reconfigure the network by changing the states of tie-switches and load demands. Computation speed is one of the major performance indicators in power grid load transfer, as a fast load transfer model can greatly reduce the economic loss of post-fault power grids. In this study, a reinforcement learning method is developed based on a deep deterministic policy gradient. The tedious training process of the reinforcement learning model can be conducted offline, so the model shows satisfactory performance in real-time operation, More >

Yunye Wan¹, Peng Chen², Yunni Xia^1,*, Yong Ma³, Dongge Zhu⁴, Xu Wang⁵, Hui Liu⁶, Weiling Li⁷, Xianhua Niu², Lei Xu⁸, Yumin Dong⁹

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.2, pp. 1997-2017, 2024, DOI:10.32604/cmes.2024.048723 - 20 May 2024

Abstract Mobile Edge Computing (MEC) is a promising technology that provides on-demand computing and efficient storage services as close to end users as possible. In an MEC environment, servers are deployed closer to mobile terminals to exploit storage infrastructure, improve content delivery efficiency, and enhance user experience. However, due to the limited capacity of edge servers, it remains a significant challenge to meet the changing, time-varying, and customized needs for highly diversified content of users. Recently, techniques for caching content at the edge are becoming popular for addressing the above challenges. It is capable of filling… More >

Abdulghani M. Abdulghani, Mokhles M. Abdulghani, Wilbur L. Walters, Khalid H. Abed^*

Intelligent Automation & Soft Computing, Vol.39, No.2, pp. 337-352, 2024, DOI:10.32604/iasc.2024.047017 - 21 May 2024

Abstract Multi-Agent Reinforcement Learning (MARL) has proven to be successful in cooperative assignments. MARL is used to investigate how autonomous agents with the same interests can connect and act in one team. MARL cooperation scenarios are explored in recreational cooperative augmented reality environments, as well as real-world scenarios in robotics. In this paper, we explore the realm of MARL and its potential applications in cooperative assignments. Our focus is on developing a multi-agent system that can collaborate to attack or defend against enemies and achieve victory with minimal damage. To accomplish this, we utilize the StarCraft… More >

Yutong Tian¹, Minghan Gao², Qiang Gao^1,*, Xiao-Hong Peng³

Intelligent Automation & Soft Computing, Vol.39, No.2, pp. 175-188, 2024, DOI:10.32604/iasc.2024.042762 - 21 May 2024

Abstract How to find an effective trading policy is still an open question mainly due to the nonlinear and non-stationary dynamics in a financial market. Deep reinforcement learning, which has recently been used to develop trading strategies by automatically extracting complex features from a large amount of data, is struggling to deal with fast-changing markets due to sample inefficiency. This paper applies the meta-reinforcement learning method to tackle the trading challenges faced by conventional reinforcement learning (RL) approaches in non-stationary markets for the first time. In our work, the history trading data is divided into multiple… More >

Yu Song¹, Xusheng Qian², Nan Zhang³, Wei Wang², Ao Xiong^1,*

CMC-Computers, Materials & Continua, Vol.79, No.2, pp. 3007-3021, 2024, DOI:10.32604/cmc.2024.051217 - 15 May 2024

Abstract To enhance the efficiency and expediency of issuing e-licenses within the power sector, we must confront the challenge of managing the surging demand for data traffic. Within this realm, the network imposes stringent Quality of Service (QoS) requirements, revealing the inadequacies of traditional routing allocation mechanisms in accommodating such extensive data flows. In response to the imperative of handling a substantial influx of data requests promptly and alleviating the constraints of existing technologies and network congestion, we present an architecture for QoS routing optimization with in Software Defined Network (SDN), leveraging deep reinforcement learning. This… More >