Search

Unused hotel rooms, unused event tickets, and unsold items are all examples of wasted expenses and earnings. Governments require accurate tourism demand forecasting in order to make informed decisions on topics such as infrastructure development and lodging site planning; therefore, accurate tourism demand forecasting becomes vital. Artificial intelligence (AI) models such as neural networks and security violation report (SVR) have been used effectively in tourist demand forecasting as a result of the fast advancement of AI. This paper constructs a tourism demand forecasting model based on machine learning on the basis of the existing forecasting model research. The completed work is as follows: (1) It introduces a large number of domestic and foreign literatures on tourism volume forecasting and proposes the research content of this paper. (2) It is proposed to stack the long short-term memory- (LSTM-) based autoencoders deeply, by adopting a hierarchical greedy pretraining method to replace the random weight initialization method used in the deep network and combining this pretraining stage and fine-tuning network together to form the SAE-LSTM prediction model for improving the performance of deep learning models. (3) This paper uses the monthly search engine strength data of city A's monthly tourist volume and its related influencing factors as the data set; processes the data set to make the model adapt to the data input; uses mean absolute error (MAE), root mean square error (RMSE), MAPE, and other model evaluation indicators; and uses LSTM and the constructed SAE-LSTM model to conduct comparative experiments to predict the number of tourist arrivals in four years. The prediction results of the models proposed in this paper are better than those of the LSTM model. According to the experimental results, the superiority of the proposed LSTM-based unsupervised pretraining method is demonstrated. [ABSTRACT FROM AUTHOR]

Aim. This comprehensive review is aimed at evaluating the diagnostic and prognostic accuracy of artificial intelligence in endodontic dentistry. Introduction. Artificial intelligence (AI) is a relatively new technology that has widespread use in dentistry. The AI technologies have primarily been used in dentistry to diagnose dental diseases, plan treatment, make clinical decisions, and predict the prognosis. AI models like convolutional neural networks (CNN) and artificial neural networks (ANN) have been used in endodontics to study root canal system anatomy, determine working length measurements, detect periapical lesions and root fractures, predict the success of retreatment procedures, and predict the viability of dental pulp stem cells. Methodology. The literature was searched in electronic databases such as Google Scholar, Medline, PubMed, Embase, Web of Science, and Scopus, published over the last four decades (January 1980 to September 15, 2021) by using keywords such as artificial intelligence, machine learning, deep learning, application, endodontics, and dentistry. Results. The preliminary search yielded 2560 articles relevant enough to the paper's purpose. A total of 88 articles met the eligibility criteria. The majority of research on AI application in endodontics has concentrated on tracing apical foramen, verifying the working length, projection of periapical pathologies, root morphologies, and retreatment predictions and discovering the vertical root fractures. Conclusion. In endodontics, AI displayed accuracy in terms of diagnostic and prognostic evaluations. The use of AI can help enhance the treatment plan, which in turn can lead to an increase in the success rate of endodontic treatment outcomes. The AI is used extensively in endodontics and could help in clinical applications, such as detecting root fractures, periapical pathologies, determining working length, tracing apical foramen, the morphology of root, and disease prediction. [ABSTRACT FROM AUTHOR]

Starting from December 2019, the global pandemic of coronavirus disease 2019 (COVID-19) is continuously expanding and has caused several millions of deaths worldwide. Fast and accurate diagnostic methods for COVID-19 detection play a vital role in containing the plague. Chest computed tomography (CT) is one of the most commonly used diagnosis methods. However, a complete CT-scan has hundreds of slices, and it is time-consuming for radiologists to check each slice to diagnose COVID-19. This study introduces a novel method for fast and automated COVID-19 diagnosis using the chest CT scans. The proposed models are based on the state-of-the-art deep convolutional neural network (CNN) architecture, and a 2D global max pooling (globalMaxPool2D) layer is used to improve the performance. We compare the proposed models to the existing state-of-the-art deep learning models such as CNN based models and vision transformer (ViT) models. Based off of metric such as area under curve (AUC), sensitivity, specificity, accuracy, and false discovery rate (FDR), experimental results show that the proposed models outperform the previous methods, and the best model achieves an area under curve of 0.9744 and accuracy 94.12% on our test datasets. It is also shown that the accuracy is improved by around 1% by using the 2D global max pooling layer. Moreover, a heatmap method to highlight the lesion area on COVID-19 chest CT images is introduced in the paper. This heatmap method is helpful for a radiologist to identify the abnormal pattern of COVID-19 on chest CT images. In addition, we also developed a freely accessible online simulation software for automated COVID-19 detection using CT images. The proposed deep learning models and software tool can be used by radiologist to diagnose COVID-19 more accurately and efficiently. [ABSTRACT FROM AUTHOR]

Pneumonia infection is the leading cause of death in young children. The commonly used pneumonia detection method is that doctors diagnose through chest X-ray, and external factors easily interfere with the results. Assisting doctors in diagnosing pneumonia in patients based on deep learning methods can effectively eliminate similar problems. However, the complex network structure and redundant parameters of deep neural networks and the limited storage and computing resources of clinical medical hardware devices make it difficult for this method to use widely in clinical practice. Therefore, this paper studies a lightweight pneumonia classification network, CPGResNet50 (ResNet50 with custom channel pruning and ghost methods), based on ResNet50 pruning and compression to better meet the application requirements of clinical pneumonia auxiliary diagnosis with high precision and low memory. First, based on the hierarchical channel pruning method, the channel after the convolutional layer in the bottleneck part of the backbone network layer is used as the pruning object, and the pruning operation is performed after its normalization to obtain a network model with a high compression ratio. Second, the pruned convolutional layers are decomposed into original convolutions and cheap convolutions using the optimized convolution method. The feature maps generated by the two convolution parts are combined as the input to the next convolutional layer. Further, we conducted many experiments using pneumonia X-ray medical image data. The results show that the proposed method reduces the number of parameters of the ResNet50 network model from 23.7 M to 3.455 M when the pruning rate is 90%, a reduction is more than 85%, FIOPs dropped from 4.12G to 523.09 M, and the speed increased by more than 85%. The model training accuracy error remained within 1%. Therefore, the proposed method has a good performance in the auxiliary diagnosis of pneumonia and obtained good experimental results. [ABSTRACT FROM AUTHOR]

It is important to study the evaluation algorithm for the stroke rehabilitation treatment effect to make accurate evaluation and optimize the stroke disease treatment plan according to the evaluation results. To address the problems of poor restoration effect of positron emission tomography (PET) image and recognition restoration effect of evaluation data and so on. In the paper, we propose a stroke rehabilitation treatment effect evaluation algorithm based on cross-modal deep learning. Magnetic resonance images (MRI) and PET of stroke patients were collected as evaluation data to construct a multimodal evaluation dataset, and the data were divided into positive samples and negative samples. According to the mapping relationship between MRI and PET, three-dimensional cyclic adversarial is used to generate the neural network model to recover the missing PET data. Using the cross-modal depth learning network model, the RGB image, depth image, gray image, and normal images of MRI and PET are taken as the feature images and the multifeature fusion method is used to fuse the feature images, output the recognition results of MRI and PET, and evaluate the effect of stroke rehabilitation treatment according to the recognition results. The results show that the proposed algorithm can accurately restore PET images, the evaluation data recognition effect is good, and the evaluation data recognition accuracy is higher than 95%. The evaluation accuracy of stroke rehabilitation treatment effect is high, the evaluation time varies between 0.56 s and 0.91 s, and the practical application effect is good. [ABSTRACT FROM AUTHOR]

Deep convolutional networks have become a powerful tool for medical imaging diagnostic. In pathology, most efforts have been focused in the subfield of histology, while cytopathology (which studies diagnostic tools at the cellular level) remains underexplored. In this paper, we propose a novel deep learning model for cancer detection from urinary cytopathology screening images. We leverage recent ideas from the field of multioutput neural networks to provide a model that can efficiently train even on small-scale datasets, such as those typically found in real-world scenarios. Additionally, we argue that calibration (i.e., providing confidence levels that are aligned with the ground truth probability of an event) has been a major shortcoming of prior works, and we experiment a number of techniques to provide a well-calibrated model. We evaluate the proposed algorithm on a novel dataset, and we show that the combination of focal loss, multiple outputs, and temperature scaling provides a model that is significantly more accurate and calibrated than a baseline deep convolutional network. [ABSTRACT FROM AUTHOR]

Meningioma is the second most commonly encountered tumor type in the brain. There are three grades of meningioma by the standards of the World Health Organization. Preoperative grade prediction of meningioma is extraordinarily important for clinical treatment planning and prognosis evaluation. In this paper, we present a new deep learning model for assisting automatic prediction of meningioma grades to reduce the recurrence of meningioma. Our model is based on an improved LeNet-5 model of convolutional neural network (CNN) and does not require the extraction of the diseased tissue, which can greatly enhance the efficiency. To address the issue of insufficient and unbalanced clinical data of meningioma images, we use an oversampling technique which allows us to considerably improve the accuracy of classification. Experiments on large clinical datasets show that our model can achieve quite high accuracy (i.e., as high as 83.33%) for the classification of meningioma images. [ABSTRACT FROM AUTHOR]

Mammography is successfully used as an effective screening tool for cancer diagnosis. A calcification cluster on mammography is a primary sign of cancer. Early researches have proved the diagnostic value of the calcification, yet their performance is highly dependent on handcrafted image descriptors. Characterizing the calcification mammography in an automatic and robust way remains a challenge. In this paper, the calcification was characterized by descriptors obtained from deep learning and handcrafted descriptors. We compared the performances of different image feature sets on digital mammograms. The feature sets included the deep features alone, the handcrafted features, their combination, and the filtered deep features. Experimental results have demonstrated that the deep features outperform handcrafted features, but the handcrafted features can provide complementary information for deep features. We achieved a classification precision of 89.32% and sensitivity of 86.89% using the filtered deep features, which is the best performance among all the feature sets. [ABSTRACT FROM AUTHOR]