The Semantic Web provides approaches and tools that allow for the processing and analysis of online content, including multimedia resources. Multimedia resources like videos, audios, and photos are increasingly common in contemporary Web content. Cinematographic works (also known as film contents) stand out among these resources as one of the most recent attractions on the Internet. An important tool employed recently in the semantic indexation of digital resources and film content is ontological annotation. This paper studies the current multimedia ontologies related to the film contents on the web. The relevant indicators were discussed comparatively, and some open issues were reviewed in details. In this way, the authors managed to integrate the metadata related to online films practically into the web of data.

In many real-world applications, it is more realistic to predict a price range than to forecast a single value. When the goal is to identify a range of prices, price prediction becomes a classification problem. The House Price Index is a typical instrument for estimating house price discrepancies. This repeat sale index analyzes the mean price variation in repeat sales or refinancing of the same assets. Since it depends on all transactions, the House Price Index is poor at projecting the price of a single house. To forecast house prices effectively, this study investigates the exploratory data analysis based on linear regression, ridge regression, Lasso regression, and Elastic Net regression, with the aid of machine learning with feature selection. The proposed prediction model for house prices was evaluated on a machine learning housing dataset, which covers 1,460 records and 81 features. By comparing the predicted and actual prices, it was learned that our model outputted an acceptable, expected values compared to the actual values. The error margin to actual values was very small. The comparison shows that our model is satisfactory in predicting house prices.

Osteoporosis is a common systemic bone disease with insidious onset and low treatment efficiency. Once it occurs, it will increase bone fragility and lead to fractures. Computed tomography (CT) is a non-invasive medical examination method that can identify the bone condition of patients. In this paper, we propose a novel channel attention module, which is subsequently integrated into the supervised deep convolutional neural network (DCNN) termed DSNet, which can perform feature fusion from two different scales, and use the method of quadratic weight calculation to enhance the interconnection among feature map channels and improve the detection and classification performance for the bone condition in lumbar spine CT images. To train and test the proposed framework, we retrospectively collect 4805 CT images of 133 patients, using DXA as the gold standard. According to the T-value diagnostic criteria defined by WHO, the vertebral bodies of L1 - L4 in CT images are labeled and classified into osteoporosis, osteopenia and normal bone mineral density. Meanwhile, the training set and test set are constructed in the ratio of 4:1. As a result, the DSNet achieves a prediction accuracy of 83.4% and a recall rate of 90.0% on the test set, indicating that the proposed model has the potential to assist clinicians in diagnosing individuals with abnormal BMD and may alert patients at high risk of osteoporosis for timely treatment.

Deep learning methods have been widely used in object detection in recent years as a result of advancements in artificial intelligence algorithms and hardware computing capacity. In light of the drawbacks of current manual testing mask wearing methods, this study offers a real-time detection method of mask wearing status based on the deep learning YOLOv5 algorithm to prevent COVID-19 and quicken the recovery of industrial production. The algorithm normalizes the original dataset, before connecting the data to the YOLOv5 network for iterative training, and saving the ideal weight data as a test set. The training and test results of the suggested approach are presented visually on a tensor board. With the help of cameras, this technique can collect faces, identify masked faces, and present prompts for mask use. According to experiment results, the suggested algorithm can match the requirements of real-world applications and has a high detection accuracy and good real-time performance.

The global child mortality rate, which is steadily declining, will be around 26 fatalities per 1000 live births in 2022. Numerous Sustainable Development Goals of the United Nations take into account the declining child mortality rate, which illustrates how far humanity has come. Cardiotocograms (CTGs) are a simple and affordable tool that most professionals choose to reduce infant and mother mortality. Three of the most cutting-edge methodologies are utilized in this research to classify the data, and their results are compared. All three classifiers outperformed the random forest, whose accuracy was 94.3%.

An estimated 9.6 million deaths, or one in every six deaths, were attributed to cancer in 2018, making it the second highest cause of death worldwide. Men are more likely to develop lung, prostate, colorectal, stomach, and liver cancer than women, who are more likely to develop breast, colorectal, lung, cervical, and thyroid cancer. The primary goals of medical image segmentation include studying anatomical structure, identifying regions of interest (RoI), and measuring tissue volume to track tumor growth. It is crucial to diagnose and treat liver lesions quickly in order to stop the tumor from spreading further. Deep learning model-based liver segmentation has become very popular in the field of medical image analysis. This study explores various deep learning-based liver lesion segmentation algorithms and methodologies. Based on the developed models, the performance, and their limitations of these methodologies are contrasted. In the end, it was concluded that small size lesion segmentation, in particular, is still an open research subject for computer-aided systems of liver lesion segmentation, for there are still a number of technical issues that need to be resolved.