Search

COVID-19 has swept the world and has had great impact on us. Rapid and accurate diagnosis of COVID-19 is essential. Analysis of chest CT images is an effective means. In this paper, an automatic diagnosis algorithm based on chest CT images is proposed. It extracts image features by stationary wavelet entropy (SWE), classifies and trains the input dataset by extreme learning machine (LEM), and finally determines the model through k-fold cross-validation (k-fold CV). By detecting 296 chest CT images of healthy individuals and COVID-19 patients, the algorithm outperforms state-of-the-art methods in sensitivity, specificity, precision, accuracy, F1, MCC, and FMI.

COVID-19 is extremely contagious and has brought serious harm to the world. Many researchers are actively involved in the study of rapid and reliable diagnostic methods for COVID-19. The study proposes a novel approach to COVID-19 diagnosis. The multiple-distance gray-level co-occurrence matrix (MDGLCM) was used to analyze chest CT images, the GA algorithm was used as an optimizer, and the feedforward neural network was used as a classifier. The results of 10 runs of 10-fold cross-validation show that the proposed method has a sensitivity of 83.38±1.40, a specificity of 81.15±2.08, a precision of 81.59±1.57, an accuracy of 82.26±0.96, an F1-score of 82.46±0.88, an MCC of 64.57±1.90, and an FMI of 82.47±0.88. The proposed MDGLCM-GA-based COVID-19 diagnosis method outperforms the other six state-of-the-art methods.

Artificial Intelligence (AI) is the enhancement and method of computer system that handles tasks which requires human like intelligence such as recognition, language translation and visual interpretation. Subjective image quality assessment (IQA) is difficult to be implemented in real-time systems, methodology for enhancing the involvement in producing IQA model is to improve the quality of image by significant evaluation. Intuitively, human eyes are not sensitive to the distortion and damage from the area with lesser visual saliency (VS), VS is closely related to IQA. With this consideration, an effective IQA was proposed, which involved two processes. The local quality map of a distorted image was computed using the structural similarity function of its feature attributes, such as brightness, chrominance and gradient. Second, the local quality map was weighted with visual saliency (VS) to get the objective evaluation of image quality. The VS was modeled by extracting the saliency of low-level features of the image, wiping off the molestation information from these saliency based on an apriori threshold, and combining the effective information to construct the saliency map. Image processing using fuzzy is gathering features and segments as fuzzy set while processing images. The experiments on the two largest database for six classical IQA metrics demonstrate that performance of weighted-VS IQA metrics is superior to the performance of no weighted-VS IQA metrics, and the proposed IQA method has higher computational accuracy than the other IQA metrics under a moderate computational complexity, especially for two types of distortion images, such as local block-wise (Block) and fast-fading (FTF).

As opposed to macro-expressions, micro-expressions are subtle and not easily detectable emotional expressions, often containing rich information about mental activities. The practical recognition of micro-expressions is essential in interrogation and healthcare. Neural networks are currently one of the most common approaches to micro-expression recognition. Still, neural networks often increase their complexity when improving accuracy, and overly large neural networks require extremely high hardware requirements for running equipment. In recent years, vision transformers based on self-attentive mechanisms have achieved accuracy in image recognition and classification that is no less than that of neural networks. Still, the drawback is that without the image-specific biases inherent to neural networks, the cost of improving accuracy is an exponential increase in the number of parameters. This approach describes training a facial expression feature extractor by transfer learning and then fine-tuning and optimizing the MobileViT model to perform the micro-expression recognition task. First, the CASME II, SAMM, and SMIC datasets are combined into a compound dataset, and macro-expression samples are extracted from the three macro-expression datasets. Each macro-expression sample and micro-expression sample are pre-processed identically to make them similar. Second, the macro-expression samples were used to train the MobileNetV2 block in MobileViT as a facial expression feature extractor and to save the weights when the accuracy was highest. Finally, some of the hyperparameters of the MobileViT model are determined by grid search and then fed into the micro-expression samples for training. The samples are classified using an SVM classifier. In the experiments, the proposed method obtained an accuracy of 84.27%, and the time to process individual samples was only 35.4 ms. Comparative experiments show that the proposed method is comparable to state-of-the-art methods in terms of accuracy while improving recognition efficiency.

Micro-expression is a kind of facial action that reflects the real emotional state of a person, and has high objectivity in emotion detection. Therefore, micro-expression recognition has become one of the research hotspots in the field of computer vision in recent years. Research with neural networks with convolutional structure is still one of the main methods of recognition. This method has the advantage of high operational efficiency and low computational complexity, but the disadvantage is its localization of feature extraction. In recent years, there are more and more plug-and-play self-attentive modules being used in convolutional neural networks to improve the ability of the model to extract global features of the samples. In this paper, we propose the ShuffleNet model combined with a miniature self-attentive module, which has only 1.53 million training parameters. First, the start frame and vertex frame of each sample will be taken out, and its TV-L1 optical flow features will be extracted. After that, the optical flow features are fed into the model for pre-training. Finally, the weights obtained from the pre-training are used as initialization weights for the model to train the complete micro-expression samples and classify them by the SVM classifier. To evaluate the effectiveness of the method, it was trained and tested on a composite dataset consisting of CASMEII, SMIC, and SAMM, and the model achieved competitive results compared to state-of-the-art methods through cross-validation of leave-one-out subjects.

According to the World Health Organization statistics, as of 25 October 2022, there have been 625,248,843 confirmed cases of COVID-19, including 65,622,281 deaths worldwide. The spread and severity of COVID-19 are alarming. The economy and life of countries worldwide have been greatly affected. The rapid and accurate diagnosis of COVID-19 directly affects the spread of the virus and the degree of harm. Currently, the classification of chest X-ray or CT images based on artificial intelligence is an important method for COVID-19 diagnosis. It can assist doctors in making judgments and reduce the misdiagnosis rate. The convolutional neural network (CNN) is very popular in computer vision applications, such as applied to biological image segmentation, traffic sign recognition, face recognition, and other fields. It is one of the most widely used machine learning methods. This paper mainly introduces the latest deep learning methods and techniques for diagnosing COVID-19 using chest X-ray or CT images based on the convolutional neural network. It reviews the technology of CNN at various stages, such as rectified linear units, batch normalization, data augmentation, dropout, and so on. Several well-performing network architectures are explained in detail, such as AlexNet, ResNet, DenseNet, VGG, GoogleNet, etc. We analyzed and discussed the existing CNN automatic COVID-19 diagnosis systems from sensitivity, accuracy, precision, specificity, and F1 score. The systems use chest X-ray or CT images as datasets. Overall, CNN has essential value in COVID-19 diagnosis. All of them have good performance in the existing experiments. If expanding the datasets, adding GPU acceleration and data preprocessing techniques, and expanding the types of medical images, the performance of CNN will be further improved. This paper wishes to make contributions to future research.

Most existing hashing methods rarely utilize the label information to learn the hashing function. However the label information of the training data is very important for classification. In this paper, we develop a new neighbor kinship preserving hashing based on a learned robust distance metric, which can pull the intra-class neighborhood samples as close as possible and push the inter-class neighborhood samples as far as possible, such that the discriminant information of the training data is incorporated into the learning framework. Furthermore, the discriminant information is inherited into the hamming space by the proposed neighbor kinship preserving hashing which can obtain highly similar binary representation for kinship neighbor pairs and highly different binary representation for non-kinship neighbor pairs. Moreover, the proposed priori intervention iterative optimization algorithm can better apply the learned discriminant information for classification and matching. Experimental results clearly demonstrate that our method achieves leading performance compared with the state-of-the-art supervised hashing learning methods.

In recent years, COVID-19 has spread rapidly among humans. Chest CT is an effective means of diagnosing COVID-19. However, the diagnosis of CT images still depends on the doctor's visual judgment and medical experience. This takes a certain amount of time and may lead to misjudgment. In this paper, a new algorithm for automatic diagnosis of COVID-19 based on chest CT image data was proposed. The algorithm comprehensively uses WE to extract image features, uses ELM for training, and finally passes k-fold CV validation. After evaluating and detecting performance on 296 chest CT images, our proposed method is superior to state-of-the-art approaches in terms of sensitivity, specificity, precision, accuracy, F1, MCC and FMI.

Currently, improving the identification of COVID-19 with the help of computer vision and artificial intelligence has received great attention from researchers. This paper proposes a novel method for automatic detection of COVID-19 based on chest CT to help radiologists improve the speed and reliability of tests for diagnosing COVID-19. Our algorithm is a hybrid approach based on the Gray-level Cooccurrence Matrix and Genetic Algorithm. The Gray-level Cooccurrence Matrix (GLCM) was used to extract CT scan image features, GA algorithm was used as an optimizer, and a feedforward neural network was used as a classifier. Finally, we use 296 chest CT scan images to evaluate the detection performance of our proposed method. To more accurately evaluate the accuracy of the algorithm, 10-run 10-fold cross-validation was introduced. Experimental results show that our proposed method outperforms state-of-the-art methods in terms of Sensitivity, Accuracy, F1, MCC, and FMI.

Nowadays, predicting students' performance is one of the most specific topics for learning environments, such as universities and schools, since it leads to the development of effective mechanisms that can enhance academic outcomes and avoid destruction. In education 4.0, Artificial Intelligence (AI) can play a key role in identifying new factors in the performance of students and implementing personalized learning, answering routine student questions, using learning analytics, and predictive modeling. It is a new challenge to redefine education 4.0 to recognize the creative and innovative intelligent students, and it is difficult to determine students' outcomes. Hence, in this paper, Hybridized Deep Neural Network (HDNN) to predict student performance in Education 4.0. The proposed HDNN method is utilized to determine the dynamics that likely influence the student's performance. The deep neural network monitor, predicts, and evaluates the student's performance in an education 4.0 environment. The findings show that the proposed HDNN method achieved better prediction accuracy when compared to other popular methods.

In this paper, a novel semi-supervised classification method, namely sparse semi-supervised classification algorithm (SSSC) is proposed. To improve the reliability of SSSC, this study extends SSSC to multi-modal features joint L 21 − norm based sparse representation. In the SSSC framework, the labeled patterns are sparsely represented by the abundance of unlabeled patterns, and then the scores of the unlabeled patterns are computed corresponding to the object class based on the relational degree vector. A quality measure is also presented to divide the unlabeled patterns into reliable and unreliable relabeled patterns. The reliable relabeled patterns are selected to be added into the labeled data for learning the labels of the unreliable relabeled data recurrently. Experimental results clearly demonstrate that the proposed method outperforms the state-of-the-art classification methods.

Most existing hashing methods usually focus on constructing hash function only, rather than learning discrete hash codes directly. Therefore the learned hash function in this way may result in the hash function which can-not achieve ideal discrete hash codes. To make the learned hash function for achieving ideal approximated discrete hash codes, in this paper, we proposed a novel supervised discrete discriminant hashing learning method, which can learn discrete hashing codes and hashing function simultaneously. To make the learned discrete hash codes to be optimal for classification, the learned hashing framework aims to learn a robust similarity metric so as to maximize the similarity of the same class discrete hash codes and minimize the similarity of the different class discrete hash codes simultaneously. The discriminant information of the training data can thus be incorporated into the learning framework. Meanwhile, the hash functions are constructed to fit the directly learned binary hash codes. Experimental results clearly demonstrate that the proposed method achieves leading performance compared with the state-of-the-art semi-supervised classification methods.

Recently, sparse representation-based classification (SRC) has received much attention for its robustness in pattern recognition. Because SRC deals with high-dimensional data, huge computational resources are required to compute sparse representations of query samples, which renders SRC solutions of high-dimensional problems infeasible. To overcome this problem, an integrated optimisation algorithm is proposed to implement feature extraction, dictionary learning and classification simultaneously. First, to obtain sparse representation coefficients, a sparsity preserving embedding map is learnt to reduce the dimensionality of the data. Second, an optimal dictionary is adaptively obtained from the training data to reduce trivial information. Third, the training samples are reclassified using sparse representation coefficients. Furthermore, the integrated learning algorithm is extended to unsupervised learning. Experimental results clearly demonstrate that the proposed method achieves better performance than several popular feature extraction and classification methods.

Scale Invariant Feature Transform (SIFT) is now the most efiective and widely used technique for feature extract. Although it has great ability in content description, there are still some problems in its feature matching. Generally, SIFT and correlative algorithms compute distance and use neighbor algorithm to look for the optimal matching couples. The disadvantages of such way are such like high complexity, instability of matching couples and so on. Especially, when huge amount of images need to be retrieved or recognized, its matching e‐ciency is very low. To solve this problem, a new matching way based on feature space division under multi-resolution is proposed in the paper. Through the algorithm, the feature space is divided into several sub-blocks under difierent resolutions. And then each sub-block is assigned to an only code. So that those feature points which are located in somewhere can be represented by the codes. At last, the feature matching can be completed through code matching, which is somehow easier to do. The experiments show that this algorithm can improve the matching e‐ciency greatly when the matching accuracy is kept as well.

In order to realize the automation and intelligence of welding process, the visual sensor and image processing technology of weld pool edge feature has become one of the key points. During the course of gas metal arc welding (GMAW), since this kind of welding requires a larger current, it makes the arc very strong and products so many droplets transfer and spatter interference. Therefore it is so difficult to extract the edge of welding pool. A new edge extraction algorithm based on component tree is proposed in the paper. It can realize the image segmentation adaptively using local features, retain the useful edge effectively and remove the false edge and noise as well. The experiments show that this algorithm can get more accurate edge information.

Training is an important means for the rehabilitation of children with autism, while the rehabilitation of athletic ability is an important content of the education and rehabilitation. This paper expounds the application of virtual campaign system rehabilitation training for children with autism advantages. Two autistic children are objects in rehabilitation training based on Kinect technology, which shows that the use of virtual system of rehabilitation training for children with autism can improve the static balance ability and coordination ability of children with autism, has an important significance to improve the lives of children with autism in self-care and social adaptation ability.