Tanvir Fatima Naik Bukht¹, Naif Al Mudawi², Saud S. Alotaibi³, Abdulwahab Alazeb², Mohammed Alonazi⁴, Aisha Ahmed AlArfaj⁵, Ahmad Jalal¹, Jaekwang Kim^6,*

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 1557-1573, 2023, DOI:10.32604/cmc.2023.041335 - 29 November 2023

Abstract Human-human interaction recognition is crucial in computer vision fields like surveillance, human-computer interaction, and social robotics. It enhances systems’ ability to interpret and respond to human behavior precisely. This research focuses on recognizing human interaction behaviors using a static image, which is challenging due to the complexity of diverse actions. The overall purpose of this study is to develop a robust and accurate system for human interaction recognition. This research presents a novel image-based human interaction recognition method using a Hidden Markov Model (HMM). The technique employs hue, saturation, and intensity (HSI) color transformation to… More >

Pham Viet Anh^1,3, Nguyen Ngoc Thuy⁴, Nguyen Long Giang², Pham Dinh Khanh⁵, Nguyen The Thuy^1,6,*

Computer Systems Science and Engineering, Vol.47, No.3, pp. 2971-2988, 2023, DOI:10.32604/csse.2023.042068 - 09 November 2023

Abstract Attribute reduction, also known as feature selection, for decision information systems is one of the most pivotal issues in machine learning and data mining. Approaches based on the rough set theory and some extensions were proved to be efficient for dealing with the problem of attribute reduction. Unfortunately, the intuitionistic fuzzy sets based methods have not received much interest, while these methods are well-known as a very powerful approach to noisy decision tables, i.e., data tables with the low initial classification accuracy. Therefore, this paper provides a novel incremental attribute reduction method to deal more… More >

Na Dong^1,*, Xiao Yang², Nasser Yousefi^3,4,*

Energy Engineering, Vol.120, No.11, pp. 2565-2583, 2023, DOI:10.32604/ee.2023.029862 - 31 October 2023

Abstract This paper proposes a modified golden jackal optimization (IGJO) algorithm to solve the OCL (which stands for optimal cooling load) problem to minimize energy consumption. In this algorithm, many tools have been developed, such as numerical visualization, local field method, competitive selection method, and iterative strategy. The IGJO algorithm is used to improve the research capabilities of the algorithm in terms of global tuning and rotation speed. In order to fully utilize the effectiveness of the proposed algorithm, three famous examples of OCL problems in basic ventilation systems were studied and compared with some previously… More >

Muayad M. Hasan^1,*, Firas K. Al-Zuhairi², Anfal H. Sadeq¹, Rana A. Azeez¹

FDMP-Fluid Dynamics & Materials Processing, Vol.19, No.11, pp. 2827-2835, 2023, DOI:10.32604/fdmp.2023.027746 - 18 September 2023

Abstract Solvents are generally used to reduce the viscosity of heavy crude oil and ultimately enhance oil recovery. Recently, a new method has been introduced where nanoparticles (NPs) are exploited to induce enhanced oil recovery owing to their ability to improve the mobility ratio, dampen the interfacial tension, and alter rock wettability. This study investigated the integration of nano-alumina (Al₂O₃) NPs with an n-hexane solvent. In particular, a Brookfield viscometer has been used to measure the crude oil viscosity and it has been found that NPs can effectively lead to a significant decrease in the overall oil More >

Ming Dong^#, Yan Wang^#, Shulin Wang, Guoyi Feng, Qian Zhang, Yongzeng Lin, Qinglong Liang, Yongqiang Wang^*, Hong Qi^*

Phyton-International Journal of Experimental Botany, Vol.92, No.10, pp. 2841-2860, 2023, DOI:10.32604/phyton.2023.030465 - 15 September 2023

Abstract Restructuring tilth layers (RTL) is a tillage method that exchanges the 0–20 and 20–40 cm soil layers that can be applied during cotton cultivation to increase cotton yield, eliminate weeds and alleviate severe disease, including Verticillium wilt. However, the mechanism by which RTL inhibits Verticillium wilt is unclear. Therefore, we investigated the distribution of microbial communities after rotary tillage (CK) and RTL treatments to identify the reasons for the reduction of Verticillium wilt in cotton fields subjected to RTL. Illumina high-throughput sequencing was used to sequence the bacterial and fungal genes. The disease incidence and More >

Yujing Ma¹, Zhongwang Wang², Xiaohui Yuan¹, Leilei Chen^2,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.27, No.2, pp. 1-2, 2023, DOI:10.32604/icces.2023.09662

Abstract The paper presents a novel fast calculation method for broadband Electromagnetic Scattering analysis. In this work, the isogeometric boundary element method is used to solve Helmholtz equations for the electromagnetic scattering problems. The non-uniform rational B-splines are employed to construct structural geometries and discretize electric and magnetic field integral equations [1,2]. To avoid timeconsuming multi-frequency calculations, the series expansion method is used to decouple the frequencydependent terms from the integrand in the boundary element method [3,4]. The second-order Arnoldi (SOAR) method is applied to construct a reduced-order model that retains the essential structures and key More >

Guangfei Jia^*, Fengwei Guo, Zhe Wu, Suxiao Cui, Jiajun Yang

Structural Durability & Health Monitoring, Vol.17, No.5, pp. 383-405, 2023, DOI:10.32604/sdhm.2023.026885 - 07 September 2023

Abstract With the development of multi-signal monitoring technology, the research on multiple signal analysis and processing has become a hot subject. Mechanical equipment often works under variable working conditions, and the acquired vibration signals are often non-stationary and nonlinear, which are difficult to be processed by traditional analysis methods. In order to solve the noise reduction problem of multiple signals under variable speed, a COT-DCS method combining the Computed Order Tracking (COT) based on Chirplet Path Pursuit (CPP) and Distributed Compressed Sensing (DCS) is proposed. Firstly, the instantaneous frequency (IF) is extracted by CPP, and the… More > Graphic Abstract

Zhen Zhong^*, Yadong Li, Yuxuan Zhao, Pengfei Ju

Sound & Vibration, Vol.57, pp. 15-27, 2023, DOI:10.32604/sv.2023.041954 - 07 September 2023

Abstract Bent-housing motor is the most widely used directional drilling tool, but it often encounters the problem of high friction when sliding drilling in horizontal wells. In this paper, a mathematical model is proposed to simulate slide drilling with a friction reduction tool of axial vibration. A term called dynamic effective tractoring force (DETF) is defined and used to evaluate friction reduction effectiveness. The factors influencing the DETF are studied, and the tool placement optimization problem is investigated. The study finds that the drilling rate of penetration (ROP) can lower the DETF but does not change… More >

Maoxia Chen^1,2,*, Qixuan Zhou¹, Jiayue Zhang¹, Jiaoyang Li¹, Wei Zhang¹, Huan Liu¹

Journal of Renewable Materials, Vol.11, No.10, pp. 3711-3723, 2023, DOI:10.32604/jrm.2023.027826 - 10 August 2023

Abstract Thermal alkaline hydrolysis is a common pretreatment method for the utilization of excess activated sludge (EAS). Owing to strict environment laws and need for better energy utilization, new methods were developed in this study to improve the efficiency of pretreatment method. Direct thermal hydrolysis (TH), pasteurized thermal hydrolysis (PTH), and alkaline pasteurized thermal hydrolysis (PTH + CaO and PTH + NaOH) methods were used to treat EAS. Each method was compared and analyzed in terms of dissolution in ammonium nitrogen (NH₄ ⁺ -N) and soluble COD (SCOD) in EAS. Furthermore, the removal of tetracycline resistance genes… More >

S. Srinivasan, K. Rajakumar^*

Computer Systems Science and Engineering, Vol.47, No.2, pp. 2481-2496, 2023, DOI:10.32604/csse.2023.040817 - 28 July 2023

Abstract

The high dimensionalhyperspectral image classification is a challenging task due to the spectral feature vectors. The high correlation between these features and the noises greatly affects the classification performances. To overcome this, dimensionality reduction techniques are widely used. Traditional image processing applications recently propose numerous deep learning models. However, in hyperspectral image classification, the features of deep learning models are less explored. Thus, for efficient hyperspectral image classification, a depth-wise convolutional neural network is presented in this research work. To handle the dimensionality issue in the classification process, an optimized self-organized map model is employed

… More >