In recent years, the improvement of people’s live standard lead to an increasing demand for travelling, but the information on scenic spots on the Internet is ponderous and the accuracy of scenic spot recommendations...
详细信息
ISBN:
(纸本)9781665402682
In recent years, the improvement of people’s live standard lead to an increasing demand for travelling, but the information on scenic spots on the Internet is ponderous and the accuracy of scenic spot recommendations is not high. This study aims to solve these problems to realize a more accurate scenic spot recommendation for self-drivings and provide a better visualization of recommendation results. A recommendation model based on the Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (MKR) algorithm is designed in this study. Then, based on this model, an intelligent knowledge graph based recommendation system for scenic spots is constructed. Rich unstructured text data of scenic spots in major scenic spot websites are crawled using Selenium and are stored and managed by the neo4j graph database. Through experimental simulation, the recommendation accuracy can reach over 84%. Compared to the Propagating User Preferences on the Knowledge Graph for Recommender Systems (RippleNet), the accuracy rate is enhanced by 6.2%.
In view of the safety hazards existing on campus,a campus safety detection system based on deep learning behavior recognition,license plate recognition and speed detection is proposed and *** design divides the campus...
详细信息
In view of the safety hazards existing on campus,a campus safety detection system based on deep learning behavior recognition,license plate recognition and speed detection is proposed and *** design divides the campus safety monitoring system into three functional modules:hazard behavior identification,license plate tracking and vehicle speed measurement,and on this basis,designs the database of storage information and the warning system of speed too fast to realize the monitoring function of campus safety.
Table Tennis is a renowned competitive and recreational sport. An Olympic sport since 1988, table tennis in-cludes several movements, shots (i.e., strokes), and positions. Consequently, many factors can affect the str...
Table Tennis is a renowned competitive and recreational sport. An Olympic sport since 1988, table tennis in-cludes several movements, shots (i.e., strokes), and positions. Consequently, many factors can affect the strokes’ accuracy and strength. This paper aims twofold: to classify the type of shot and to enhance the performance of the classification by improving the recognition accuracy and reducing the computational time. To track the movement of the body parts and extract table tennis stroke information, sensors (both Accelerometers and Gyroscopes) were utilized. The extracted data are processed and passed to a P–Dollar classifier to recognize six different table tennis strokes. This work utilizes two classification approaches to evaluate the performance, both linear and hierarchical. The presented results demonstrate that the hierarchical classification yields a better accuracy of 88%, achieved in 4 seconds, while traditional linear classification achieved 83% within 6 seconds.
In the context of advancing technologies in the entertainment industry, this study explores the utilization of machine learning (ML) for assessing actors' performances. The integration of technology in that indust...
详细信息
ISBN:
(数字)9798350367775
ISBN:
(纸本)9798350367782
In the context of advancing technologies in the entertainment industry, this study explores the utilization of machine learning (ML) for assessing actors' performances. The integration of technology in that industry is limited. The methodology encompasses acquiring performance ratings from the model to recognize predefined criteria. These ratings are then subjected to comparative analysis to gauge the system's effectiveness. The system showed 83.2% accuracy using MediaPipe to extract the positions of body part points for each gesture. Then, using One Dollar Py library, positive, mediocre, and negative models are developed using the patterns extracted from MediaPipe. We benchmarked the system against an assessment by a professional director. This work suggests a pathway to the use of Machine Learning tools in the industry and could be viewed as an innovative method for automating performance assessment with real-world applications that extend across the film-making process.
Parkinson's disease (PD) profoundly impacts millions in Sri Lanka, emphasizing the importance of early detection for better patient outcomes. We introduce “NeuraTrace PD,” an innovative application for early PD ...
Parkinson's disease (PD) profoundly impacts millions in Sri Lanka, emphasizing the importance of early detection for better patient outcomes. We introduce “NeuraTrace PD,” an innovative application for early PD screening, combining brain MRI, hand-drawn image analysis, facial expression assessment, and voice analysis. For brain MRI analysis, we employed a Graph Convolutional Network (GCN), achieving an impressive accuracy of 91% and identifying distinct graph connectivity patterns using graph theory. We also use a deep Convolutional Neural Network (CNN) to reach 90% accuracy in analyzing hand-drawn images, while optimizing image resolution for efficiency and information retention. Facial expression analysis is a vital component, leveraging CNN and Constrained Local Models (CLM) to accurately extract Facial Action Units (FAUs), which contribute to a remarkable 95% accuracy using the XGBoost machine learning model. We introduce a Machine Learning (ML) algorithm and advanced signal processing to enhance voice feature analysis, offering a thorough understanding and classification of PD patients. It reaches 99% accuracy. In summary, our approach holds significant promise for advancing early PD diagnosis, ultimately improving the quality of life for those affected by this challenging condition.
For centuries, the economy of Sri Lanka has been backed by the agricultural sector. Even though it has contributed to the development of the nation on a large scale, the economies and living standards of the farmers h...
详细信息
This study aims at designing Map Reduce and federated learning-based asthma prediction model for adolescent to provide answers to the problems associated with the existing asthma prediction model for adolescent. This ...
详细信息
ISBN:
(数字)9798350358155
ISBN:
(纸本)9798350358162
This study aims at designing Map Reduce and federated learning-based asthma prediction model for adolescent to provide answers to the problems associated with the existing asthma prediction model for adolescent. This study leveraged on two diverse datasets: the Nigerian Hospital Asthma dataset and the National Survey of Children Health dataset for benchmarking purposes. Symmetrical uncertainty and normalization interaction were employed for feature selection. The model was trained using Federated Artificial Intelligence (AI) Technology Enabler (FATE) and complemented with XGBoost model and one central server for federated algorithm averaging. The study was implemented with python programming language on Google Collaboratory environment. The results of the analysis showed considerable high accuracy of 0.98, precision (0.98%), recall (0.98%) and F1-socre (0.99%) for the asthmatic class and precision of 0.98%, recall of 0.98%, as well as F1-score of 0.99% for the non-asthmatic class. The implemented model was benchmark with the existing asthma prediction models in the literature. Simulated attack was also performed using implemented model with and without Map Reduce. This study concludes that the researchers’ model has the potentials to outperform some of the existing machine learning models on asthma prediction in adolescent, thereby facilitating collaborative sharing of the model with other hospitals, protect the patient information from leakage, meeting the criteria of healthcare data protection regulation as well as beneficial for enhancing the security of the dataset.
Phishing is a cyber threat where attackers create deceptive websites or emails to exploit individuals for fraudulent purposes such as providing sensitive information like usernames, passwords, or financial details. He...
详细信息
Facial expressions are important information that reflects human *** dynamic expressions of students in class,8 kinds of emotions are selected for application:positive emotions: "happy";negative emotions: &q...
详细信息
Facial expressions are important information that reflects human *** dynamic expressions of students in class,8 kinds of emotions are selected for application:positive emotions: "happy";negative emotions: "disgust,Sadness,doubts,contempt,anger";neutral emotion: "focus,surprise". In this design,the classroom performance scoring system in normal hours is split into four functions:wireless network list acquisition and verification,face recognition,emotion analysis,and scoring record *** this basis,SVM and Softmax are *** expression recognition and a data storage database is designed to realize the function of an intelligent scoring system for classroom performance *** solve this problem,an expression recognition method combining pyramid convolutional neural network and attention mechanism is proposed.
Thanks to recent developments in explainable Deep Learning models, researchers have shown that these models can be incredibly successful and provide encouraging results. However, a lack of model interpretability can h...
详细信息
暂无评论