Badriyya B. Al-onazi¹, Najm Alotaibi², Jaber S. Alzahrani³, Hussain Alshahrani⁴, Mohamed Ahmed Elfaki⁴, Radwa Marzouk⁵, Mahmoud Othman⁶, Abdelwahed Motwakel^7,*

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 1537-1554, 2023, DOI:10.32604/cmc.2023.034196

Abstract Text classification or categorization is the procedure of automatically tagging a textual document with most related labels or classes. When the number of labels is limited to one, the task becomes single-label text categorization. The Arabic texts include unstructured information also like English texts, and that is understandable for machine learning (ML) techniques, the text is changed and demonstrated by numerical value. In recent times, the dominant method for natural language processing (NLP) tasks is recurrent neural network (RNN), in general, long short term memory (LSTM) and convolutional neural network (CNN). Deep learning (DL) models are currently presented for deriving… More >

Zhaoting Liu¹, Jianbo Wu^1,*, Sha He², Xin Rao³, Shiqiang Wang², Shen Wang¹, Wei Wei⁴

Structural Durability & Health Monitoring, Vol.17, No.4, pp. 299-314, 2023, DOI:10.32604/sdhm.2023.022554

Abstract It is known that eddy current effect has a great influence on magnetic flux leakage testing (MFL). Usually, contact-type encoder wheels are used to measure MFL testing speed to evaluate the effect and further compensate testing signals. This speed measurement method is complicated, and inevitable abrasion and occasional slippage will reduce the measurement accuracy. In order to solve this problem, based on eddy current effect due to the relative movement, a speed measurement method is proposed, which is contactless and simple. In the high-speed MFL testing, eddy current induced in the specimen will cause an obvious modification to the applied… More > Graphic Abstract

Yousif Sufyan Jghef¹, Mohammed Jasim Mohammed Jasim², Subhi R. M. Zeebaree^3,*, Rizgar R. Zebari⁴

Computer Systems Science and Engineering, Vol.47, No.2, pp. 1651-1664, 2023, DOI:10.32604/csse.2023.037449

Abstract Wireless Sensor Networks (WSNs) gather data in physical environments, which is some type. These ubiquitous sensors face several challenges responsible for corrupting them (mostly sensor failure and intrusions in external agents). WSNs were disposed to error, and effectual fault detection techniques are utilized for detecting faults from WSNs in a timely approach. Machine learning (ML) was extremely utilized for detecting faults in WSNs. Therefore, this study proposes a billiards optimization algorithm with modified deep learning for fault detection (BIOMDL-FD) in WSN. The BIOMDLFD technique mainly concentrates on identifying sensor faults to enhance network efficiency. To do so, the presented BIOMDL-FD… More >

Mahmoud Ragab^1,2,*, Sultanah M. Alshammari^2,3, Abdullah S. Al-Malaise Al-Ghamdi^2,4

Computer Systems Science and Engineering, Vol.47, No.2, pp. 2497-2512, 2023, DOI:10.32604/csse.2023.041446

Abstract The Internet of Things (IoT) system has confronted dramatic growth in high dimensionality and data traffic. The system named intrusion detection systems (IDS) is broadly utilized for the enhancement of security posture in an IT infrastructure. An IDS is a practical and suitable method for assuring network security and identifying attacks by protecting it from intrusive hackers. Nowadays, machine learning (ML)-related techniques were used for detecting intrusion in IoTs IDSs. But, the IoT IDS mechanism faces significant challenges because of physical and functional diversity. Such IoT features use every attribute and feature for IDS self-protection unrealistic and difficult. This study… More >

Amnart Boonloi^a, Withada Jedsadaratanachai^b,*

Frontiers in Heat and Mass Transfer, Vol.10, pp. 1-19, 2018, DOI:10.5098/hmt.10.6

Abstract Convective heat transfer, pressure loss and thermal performance in a heat exchanger tube inserted with the modified V-shaped baffle are investigated numerically. The influences of the flow attack angle (α = 20o , 30o and 45o ), baffle height in term of blockage ratio (b/D = BR = 0.05, 0.10, 0.15, 0.20 and 0.25) and arrangement (The V-tip pointing downstream is called “V-Downstream”, while the V-tip pointing upstream is named “V-Upstream”.) on heat transfer and friction loss are presented for the Reynolds number in range 100 – 1200 (laminar region). The numerical study (finite volume method) is selected to solve… More >

Wenjing Xia^1,*, JinHui Wang¹, Tao Xu¹, Nan Jiang²

Journal of Renewable Materials, Vol.11, No.8, pp. 3387-3402, 2023, DOI:10.32604/jrm.2023.026971

Abstract To understand the effects of filler-asphalt ratio on different properties of lignin and polyester fiber reinforced shape memory polyurethane (SMPU)/styrene butadiene styrene (SBS) composite modified asphalt mortar (PSAM), as well as to reveal the reinforcing and toughening mechanisms of lignin and polyester fibers on PSAM, SMPU, SBS and mineral powder were first utilized to prepare PSAM. Then the conventional, rheological and anticracking properties of lignin fiber reinforced PSAM (LFAM) and polyester fiber reinforced PSAM (PFAM) at different filler-asphalt ratios were characterized. Test results indicate that the shear strength, deformation resistance and viscosity are increased after adding 0.8wt% lignin fiber or… More > Graphic Abstract

Jiaxing Sun¹, Lili Ji^1,*, Qianrui He¹, Ran Li¹, Xiaoyue Xia², Yaning Wang¹, Yi Yang², Lu Cai³, Jian Guo²

Journal of Renewable Materials, Vol.11, No.8, pp. 3227-3243, 2023, DOI:10.32604/jrm.2023.027160

Abstract

In this study, a novel absorpent (MSAR600°C) with a hydrophobic surface and hierarchical porous structure for the removal of kitchen oil was facilely fabricated from the macroalgae, laver (Porphyra haitanensis) by incorporating high-temperature carbonization and alkyl polyglucosides (APG) and rhamnolipid (RL) surfactants modification. The characterization results showed MSAR600°C possessed a louts-leaf-like papillae microstructure with high contact angle (137.5°), abundant porous structure with high specific surface area (23.4 m²/g), and various oxygen-containing functional groups (-OH, C=O, C-O). Batch adsorption experiments were conducted to investigate the effect of adsorption time, temperature, pH, and absorbent dose on kitchen oil adsorption performance. Then the… More > Graphic Abstract

Zhiwei Ye¹, Ziqian Fang¹, Zhina Song^1,*, Haigang Sui², Chunyan Yan¹, Wen Zhou¹, Mingwei Wang¹

Intelligent Automation & Soft Computing, Vol.37, No.2, pp. 2019-2035, 2023, DOI:10.32604/iasc.2023.039949

Abstract Hyperparameters play a vital impact in the performance of most machine learning algorithms. It is a challenge for traditional methods to configure hyperparameters of the capsule network to obtain high-performance manually. Some swarm intelligence or evolutionary computation algorithms have been effectively employed to seek optimal hyperparameters as a combinatorial optimization problem. However, these algorithms are prone to get trapped in the local optimal solution as random search strategies are adopted. The inspiration for the hybrid rice optimization (HRO) algorithm is from the breeding technology of three-line hybrid rice in China, which has the advantages of easy implementation, less parameters and… More >

Nur Fairuz Mohamed Yusof¹, Dahaman Ishak², Muhammad Ammirrul Atiqi Mohd Zainuri^3,*, Muhammad Najwan Hamidi², Zuhair Muhammed Alaas⁴, Mohamed Mostafa Ramadan Ahmed⁵

Intelligent Automation & Soft Computing, Vol.37, No.2, pp. 2441-2457, 2023, DOI:10.32604/iasc.2023.037778

Abstract Grid-connected reactive-load compensation and harmonic control are becoming a central topic as photovoltaic (PV) grid-connected systems diversified. This research aims to produce a high-performance inverter with a fast dynamic response for accurate reference tracking and a low total harmonic distortion (THD) even under nonlinear load applications by improving its control scheme. The proposed system is expected to operate in both stand-alone mode and grid-connected mode. In stand-alone mode, the proposed controller supplies power to critical loads, alternatively during grid-connected mode provide excess energy to the utility. A modified variable step incremental conductance (VS-InCond) algorithm is designed to extract maximum power… More >

Jae Gun Kwak¹, Eung Re Kim², Taeyoung Yun¹, Sungkyu Cho¹, Chang-Ha Lee², Woong-Han Kim^1,*

Congenital Heart Disease, Vol.18, No.3, pp. 325-336, 2023, DOI:10.32604/chd.2023.027758

Abstract Objectives: To access the effectiveness of our modified right-ventricular overhauling procedure on tricuspid valve (TV) growth in patients with pulmonary atresia with intact ventricular septum (PAIVS). Methods: We retrospectively reviewed 21 patients with PAIVS who underwent modified right ventricular overhauling (mRVoh) between 2008 and 2019 at two institutions. Our mRVoh consisted of wide resection of hypertrophied infundibular and trabecular muscle, peeling off fibrotic endocardial tissue in the right ventricle (RV) cavity, surgical pulmonary valvotomy, and Blalock-Taussig shunt or banding of ductus arteriosus under cardiopulmonary bypass. The TV annulus sizes were measured and analyzed using echocardiography before and after mRVoh. Results:… More > Graphic Abstract