Sakorn Mekruksavanich¹, Narit Hnoohom², Anuchit Jitpattanakul^3,4,*

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 2669-2686, 2023, DOI:10.32604/iasc.2023.038549

Abstract Recognition of human activity is one of the most exciting aspects of time-series classification, with substantial practical and theoretical implications. Recent evidence indicates that activity recognition from wearable sensors is an effective technique for tracking elderly adults and children in indoor and outdoor environments. Consequently, researchers have demonstrated considerable passion for developing cutting-edge deep learning systems capable of exploiting unprocessed sensor data from wearable devices and generating practical decision assistance in many contexts. This study provides a deep learning-based approach for recognizing indoor and outdoor movement utilizing an enhanced deep pyramidal residual model called SenPyramidNet and motion information from wearable… More >

Yabin Yang^1,*, Yanfei Wang¹, Quan Li²

The International Conference on Computational & Experimental Engineering and Sciences, Vol.25, No.1, pp. 1-1, 2023, DOI:10.32604/icces.2023.09842

Abstract Residual stresses and deformations are one of the challenges needs to solve for metal additive manufacturing part. Finite element method plays an important role in predicting the residual stresses and deformations to reduce the experimental costs, and provides a powerful tool for the optimization of process parameters and scanning strategies of heat source. However, the key problem in simulation is the mismatch between the melt pool and the built part in both spatial and temporal scale. This would result in large discretization in both spatial and temporal domains in the simulation, which gives rise to huge computational cost. Therefore, it… More >

Gang Liu¹, Xinqi Chen^2,3,*, Lijuan Bao¹, Linbo Xu^2,3, Chaochao Dai¹, Lei Yang^2,3, Chengmin Wang⁴

Structural Durability & Health Monitoring, Vol.17, No.4, pp. 337-351, 2023, DOI:10.32604/sdhm.2022.023583

Abstract Aiming at the fact that the rotor winding inter-turn weak faults can hardly be detected due to the strong electromagnetic coupling effect in the excitation system, an interval observer based on current residual is designed. Firstly, the mechanism of the inter-turn short circuit of the rotor winding in the excitation system is modeled under the premise of stable working conditions, and electromagnetic decoupling and system simplification are carried out through Park Transform. An interval observer is designed based on the current residual in the two-phase coordinate system, and the sensitive and stable conditions of the observer is preset. The fault… More >

Yu Zhang^1,2,3, Mingkui Zhang^1,2,*, Jitao Li^1,2, Guangshu Chen^1,2

Computer Systems Science and Engineering, Vol.47, No.2, pp. 1987-2006, 2023, DOI:10.32604/csse.2023.040381

Abstract Rockburst is a phenomenon in which free surfaces are formed during excavation, which subsequently causes the sudden release of energy in the construction of mines and tunnels. Light rockburst only peels off rock slices without ejection, while severe rockburst causes casualties and property loss. The frequency and degree of rockburst damage increases with the excavation depth. Moreover, rockburst is the leading engineering geological hazard in the excavation process, and thus the prediction of its intensity grade is of great significance to the development of geotechnical engineering. Therefore, the prediction of rockburst intensity grade is one problem that needs to be… More >

Narit Hnoohom¹, Sakorn Mekruksavanich², Anuchit Jitpattanakul^3,4,*

Intelligent Automation & Soft Computing, Vol.37, No.2, pp. 1275-1291, 2023, DOI:10.32604/iasc.2023.038584

Abstract In recent years, as intelligent transportation systems (ITS) such as autonomous driving and advanced driver-assistance systems have become more popular, there has been a rise in the need for different sources of traffic situation data. The classification of the road surface type, also known as the RST, is among the most essential of these situational data and can be utilized across the entirety of the ITS domain. Recently, the benefits of deep learning (DL) approaches for sensor-based RST classification have been demonstrated by automatic feature extraction without manual methods. The ability to extract important features is vital in making RST… More >

CH. Mohan Sai Kumar^*, R. S. Valarmathi

Intelligent Automation & Soft Computing, Vol.37, No.2, pp. 1711-1728, 2023, DOI:10.32604/iasc.2023.038113

Abstract Image dehazing is a rapidly progressing research concept to enhance image contrast and resolution in computer vision applications. Owing to severe air dispersion, fog, and haze over the environment, hazy images pose specific challenges during information retrieval. With the advances in the learning theory, most of the learning-based techniques, in particular, deep neural networks are used for single-image dehazing. The existing approaches are extremely computationally complex, and the dehazed images are suffered from color distortion caused by the over-saturation and pseudo-shadow phenomenon. However, the slow convergence rate during training and haze residual is the two demerits in the conventional image… More >

Wajiha Rahim Khan¹, Tahir Mustafa Madni¹, Uzair Iqbal Janjua¹, Umer Javed², Muhammad Attique Khan³, Majed Alhaisoni⁴, Usman Tariq⁵, Jae-Hyuk Cha^6,*

CMC-Computers, Materials & Continua, Vol.76, No.1, pp. 647-664, 2023, DOI:10.32604/cmc.2023.039188

Abstract Segmenting brain tumors in Magnetic Resonance Imaging (MRI) volumes is challenging due to their diffuse and irregular shapes. Recently, 2D and 3D deep neural networks have become famous for medical image segmentation because of the availability of labelled datasets. However, 3D networks can be computationally expensive and require significant training resources. This research proposes a 3D deep learning model for brain tumor segmentation that uses lightweight feature extraction modules to improve performance without compromising contextual information or accuracy. The proposed model, called Hybrid Attention-Based Residual Unet (HA-RUnet), is based on the Unet architecture and utilizes residual blocks to extract low-… More >

Zhiqiang Wu^*, Bing Xie

Computer Systems Science and Engineering, Vol.47, No.1, pp. 299-316, 2023, DOI:10.32604/csse.2023.038586

Abstract Image has become an essential medium for expressing meaning and disseminating information. Many images are uploaded to the Internet, among which some are pornographic, causing adverse effects on public psychological health. To create a clean and positive Internet environment, network enforcement agencies need an automatic and efficient pornographic image recognition tool. Previous studies on pornographic images mainly rely on convolutional neural networks (CNN). Because of CNN’s many parameters, they must rely on a large labeled training dataset, which takes work to build. To reduce the effect of the database on the recognition performance of pornographic images, many researchers view pornographic… More >

Jing Hu^a,* , Mingxing Du^b

Frontiers in Heat and Mass Transfer, Vol.14, pp. 1-7, 2020, DOI:10.5098/hmt.14.5

Abstract Inert gases are conveniently used for leak detection. Relative to CO₂, majority of the inert gases are non-condensable. It is of great significance to understand the effects of residual non-condensable gases on the performance of a refrigeration system. This paper investigates, both theoretically and experimentally, on the impact of residual non-condensable gases on the performance of a carbon dioxide (CO₂) evaporator and the system performance. A theoretical analysis indicates that residual non-condensable gases can convert homogeneous nucleation into a heterogeneous nucleation process and accelerate phase change, thus, reducing superheat or incipient boiling temperature. To investigate the influence of residual non-condensable… More >

ALESSANDRO GOZZETTI^*, MONICA BOCCHIA

Oncology Research, Vol.31, No.3, pp. 271-274, 2023, DOI:10.32604/or.2023.028668

Abstract Novel drug availability has increased the depth of response and revolutionised the outcomes of multiple myeloma patients. Minimal residual disease evaluation is a surrogate for progression-free survival and overall survival and has become widely used not-only in clinical trials but also in daily patient management. Bone marrow aspiration is the gold standard for response evaluation, but due to the patchy nature of myeloma, false negatives are possible. Liquid biopsy and blood-based minimal residual disease evaluation consider circulating plasma cells, mass spectrometry or circulating tumour DNA. This approach is less invasive, can provide a more comprehensive picture of the disease and… More >