Huanhua Liu, Wei Wang^*, Hanyu Liu, Shuheng Yi, Yonghao Yu, Xunwen Yao

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.1, pp. 459-472, 2024, DOI:10.32604/cmes.2023.029084

Abstract Deep Convolutional Neural Networks (CNNs) have achieved high accuracy in image classification tasks, however, most existing models are trained on high-quality images that are not subject to image degradation. In practice, images are often affected by various types of degradation which can significantly impact the performance of CNNs. In this work, we investigate the influence of image degradation on three typical image classification CNNs and propose a Degradation Type Adaptive Image Classification Model (DTA-ICM) to improve the existing CNNs’ classification accuracy on degraded images. The proposed DTA-ICM comprises two key components: a Degradation Type Predictor (DTP) and a Degradation Type… More >

Jianying Shi¹, Shengchao Chen¹, Benguo Yu², Yi Ren^3,*, Guanjun Wang^1,4,*, Chenyang Xue⁵

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 3235-3258, 2023, DOI:10.32604/iasc.2023.041392

Abstract Respiratory infections in children increase the risk of fatal lung disease, making effective identification and analysis of breath sounds essential. However, most studies have focused on adults ignoring pediatric patients whose lungs are more vulnerable due to an imperfect immune system, and the scarcity of medical data has limited the development of deep learning methods toward reliability and high classification accuracy. In this work, we collected three types of breath sounds from children with normal (120 recordings), bronchitis (120 recordings), and pneumonia (120 recordings) at the posterior chest position using an off-the-shelf 3M electronic stethoscope. Three features were extracted from… More >

Motasem S. Alsawadi^1,*, El-Sayed M. El-kenawy², Miguel Rio¹

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 2767-2782, 2023, DOI:10.32604/iasc.2023.039440

Abstract The BlazePose, which models human body skeletons as spatiotemporal graphs, has achieved fantastic performance in skeleton-based action identification. Skeleton extraction from photos for mobile devices has been made possible by the BlazePose system. A Spatial-Temporal Graph Convolutional Network (STGCN) can then forecast the actions. The Spatial-Temporal Graph Convolutional Network (STGCN) can be improved by simply replacing the skeleton input data with a different set of joints that provide more information about the activity of interest. On the other hand, existing approaches require the user to manually set the graph’s topology and then fix it across all input layers and samples.… More >

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 >

Shoutao Li^1,2,*, Ruyi Qu¹, Yu Zhang¹, Dingli Yu³

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 2809-2823, 2023, DOI:10.32604/iasc.2023.036999

Abstract Freezing of Gait (FOG) is the most common and disabling gait disorder in patients with Parkinson’s Disease (PD), which seriously affects the life quality and social function of patients. This paper proposes a FOG recognition method based on the Variational Mode Decomposition (VMD). Firstly, VMD instead of the traditional time-frequency analysis method to complete adaptive decomposition to the FOG signal. Secondly, to improve the accuracy and speed of the recognition algorithm, use the CART model as the base classifier and perform the feature dimension reduction. Then use the RUSBoost ensemble algorithm to solve the problem of unbalanced sample size and… More >

Huafei Yang¹, Wenqing Yang¹, Nan Zhang¹, Shanming Wei^2,*, Yingnan Shang¹

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 2745-2765, 2023, DOI:10.32604/iasc.2023.036614

Abstract Equipment defect detection is essential to the security and stability of power grid networking operations. Besides the status of the power grid itself, environmental information is also necessary for equipment defect detection. At the same time, different types of intelligent sensors can monitor environmental information, such as temperature, humidity, dust, etc. Therefore, we apply the Internet of Things (IoT) technology to monitor the related environment and pervasive interconnections to diverse physical objects. However, the data related to device defects in the existing Internet of Things are complex and lack uniform association hence building a knowledge graph is proposed to solve… More >

Mesfer Al Duhayyim^1,*, Hala J. Alshahrani², Khaled Tarmissi³, Heyam H. Al-Baity⁴, Abdullah Mohamed⁵, Ishfaq Yaseen⁶, Amgad Atta Abdelmageed⁶, Mohamed I. Eldesouki⁷

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 2549-2566, 2023, DOI:10.32604/iasc.2023.034827

Abstract Computational linguistics is an engineering-based scientific discipline. It deals with understanding written and spoken language from a computational viewpoint. Further, the domain also helps construct the artefacts that are useful in processing and producing a language either in bulk or in a dialogue setting. Named Entity Recognition (NER) is a fundamental task in the data extraction process. It concentrates on identifying and labelling the atomic components from several texts grouped under different entities, such as organizations, people, places, and times. Further, the NER mechanism identifies and removes more types of entities as per the requirements. The significance of the NER… More >

Jinxing Niu^1,*, Shaokui Gu¹, Junmin Du², Yongxing Hao¹

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 2015-2031, 2023, DOI:10.32604/cmc.2023.040489

Abstract With the continuous development of the economy and society, plastic pollution in rivers, lakes, oceans, and other bodies of water is increasingly severe, posing a serious challenge to underwater ecosystems. Effective cleaning up of underwater litter by robots relies on accurately identifying and locating the plastic waste. However, it often causes significant challenges such as noise interference, low contrast, and blurred textures in underwater optical images. A weighted fusion-based algorithm for enhancing the quality of underwater images is proposed, which combines weighted logarithmic transformations, adaptive gamma correction, improved multi-scale Retinex (MSR) algorithm, and the contrast limited adaptive histogram equalization (CLAHE)… More >

Youngeun An, Jimin Lee, EunSang Bak^*, Sungbum Pan^*

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 1817-1832, 2023, DOI:10.32604/cmc.2023.039460

Abstract Emotion recognition based on facial expressions is one of the most critical elements of human-machine interfaces. Most conventional methods for emotion recognition using facial expressions use the entire facial image to extract features and then recognize specific emotions through a pre-trained model. In contrast, this paper proposes a novel feature vector extraction method using the Euclidean distance between the landmarks changing their positions according to facial expressions, especially around the eyes, eyebrows, nose, and mouth. Then, we apply a new classifier using an ensemble network to increase emotion recognition accuracy. The emotion recognition performance was compared with the conventional algorithms… More >

So-Yeon Lee¹, Jihoon Park¹, Dae-Young Kim^2,*

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 1497-1514, 2023, DOI:10.32604/cmc.2023.034914

Abstract Recently, to build a smart factory, research has been conducted to perform fault diagnosis and defect detection based on vibration and noise signals generated when a mechanical system is driven using deep-learning technology, a field of artificial intelligence. Most of the related studies apply various audio-feature extraction techniques to one-dimensional raw data to extract sound-specific features and then classify the sound by using the derived spectral image as a training dataset. However, compared to numerical raw data, learning based on image data has the disadvantage that creating a training dataset is very time-consuming. Therefore, we devised a two-step data preprocessing… More >