This survey paper presents a brief overview of recent research on graph data augmentation and few-shot learning. It covers various techniques for graph data augmentation, including node and edge perturbation, graph co...
This survey paper presents a brief overview of recent research on graph data augmentation and few-shot learning. It covers various techniques for graph data augmentation, including node and edge perturbation, graph coarsening, and graph generation, as well as the latest developments in few-shot learning, such as meta-learning and model-agnostic meta-learning. The paper explores these areas in depth and delves into further sub classifications. Rule based approaches and learning based approaches are surveyed under graph augmentation techniques. Few-Shot Learning on graphs is also studied in terms of metric-learning techniques and optimization-based techniques. In all, this paper provides an extensive array of techniques that can be employed in solving graph processing problems faced in low-data scenarios.
In marine ecosystems, flatworm species feed on economically important species such as oysters and could increase the mortality and thereby lower the yield. Understanding the behavior of flatworms in response to enviro...
详细信息
ISBN:
(纸本)9798218142186
In marine ecosystems, flatworm species feed on economically important species such as oysters and could increase the mortality and thereby lower the yield. Understanding the behavior of flatworms in response to environmental factors and, more importantly, knowing the distribution patterns of the flatworms in the field is crucial and has important implications for fishery management. Currently, the dominant methods for flatworm observation are all Kalman Filter-based. However, the traditional Kalman Filter-based tracking algorithms were mostly based only on one single frame as the reference template for the tracking of the target while flatworms are highly deformable targets that can have a great degree of shape-shifting. Here, we proposed a workflow of flatworm tracking using deep learning module (YOLOV5 and StrongSort) to track flatworm movement with high accuracy. We conducted a series of food choice essay experiments and verified our workflow by tracking movement and reporting the trajectory of the subject flatworm species. We use data refinement algorithm based on the similarity of images to greatly reduce the dataset size to allow for faster training speed. We used the workflow developed in this study to track the flatworm specimen in different experiment videos and achieved a 100% successful tracking rate (STR) in the tracking of the target. In addition, the tracking method was deployed on edge computing device Nvidia Jetson Nano with the achievement of 7 frames per second, indicating the capability of our algorithm in real-time tracking. More importantly, our workflow successfully detected and then tracked the movement of target flatworm specimen in all experiment videos. Based on the tracking data, we computed the trajectory and the moving speed of the flatworm. It is expected that this algorithm could be further applied to field video data for the tracking of flatworm, particularly the tracking of S. eliptica, and thereby assisting the study of benthic ecol
This paper introduces the jazznet dataset, a dataset of fundamental jazz piano music patterns for developing machine learning (ML) algorithms in music information retrieval (MIR). The dataset contains 162520 labeled p...
详细信息
This paper introduces the jazznet dataset, a dataset of fundamental jazz piano music patterns for developing machine learning (ML) algorithms in music information retrieval (MIR). The dataset contains 162520 labeled piano patterns, including chords, arpeggios, scales, and chord progressions with their inversions, resulting in more than 26k hours of audio and a total size of 95GB. The paper explains the dataset’s composition, creation, and generation, and presents an open-source Pattern Generator using a method called Distance-Based Pattern Structures (DBPS), which allows researchers to easily generate new piano patterns simply by defining the distances between pitches within the musical patterns. We demonstrate that the dataset can help researchers benchmark new models for challenging MIR tasks, using a convolutional recurrent neural network (CRNN) and a deep convolutional neural network. The dataset and code are available via: https://***/tosiron/jazznet.
With the advances in deep learning, speech enhancement systems benefited from large neural network architectures and achieved state-of-the-art quality. However, speaker-agnostic methods are not always desirable, both ...
详细信息
With the advances in deep learning, speech enhancement systems benefited from large neural network architectures and achieved state-of-the-art quality. However, speaker-agnostic methods are not always desirable, both in terms of quality and their complexity, when they are to be used in a resource-constrained environment. One promising way is personalized speech enhancement (PSE), which is a smaller and easier speech enhancement problem for small models to solve, because it focuses on a particular test-time user. To achieve the personalization goal, while dealing with the typical lack of personal data, we investigate the effect of data augmentation based on neural speech synthesis (NSS). In the proposed method, we show that the quality of the NSS system’s synthetic data matters, and if they are good enough the augmented dataset can be used to improve the PSE system that outperforms the speaker-agnostic baseline. The proposed PSE systems show significant complexity reduction while preserving the enhancement quality.
Social media has a very significant influence on numerous fields in the modern world. These social media platforms generate big data that can be used to analyze an event. The impacts of catastrophic events like natura...
Social media has a very significant influence on numerous fields in the modern world. These social media platforms generate big data that can be used to analyze an event. The impacts of catastrophic events like natural disasters could be efficiently managed by the analysis of this huge amount of data. Information-sharing platforms like Twitter have proven extremely helpful in gathering information to offer data linked to relief efforts run by NGOs or volunteers. The extraction of tweets from the Twitter platform using the Twitter application programming interface, their classification into “need of resources,” “availability of resources,” and irrelevant tweets with the help of deep learning, clustering, and various natural language processing techniques like BERT, distilBERT, RF, LR, NB, and SVM classification models, and the comparison of their results are aimed to be conducted in this research.
Employee turnover and customer churn a significant challenges for organizations worldwide. The loss of employees can significantly impact the company's growth and success, from decreased productivity to increased ...
Employee turnover and customer churn a significant challenges for organizations worldwide. The loss of employees can significantly impact the company's growth and success, from decreased productivity to increased costs, including recruiting and training new employees. To mitigate this problem, many organizations are adopting artificial intelligence (AI) techniques to detect employee churn. In this approach, AI algorithms like KNN, Decision Tree, Logistic Regression, Random Forest, SVM (Support Vector Machines), ADA boost, Naïve Bayes, and GBM(Gradient Boosted Machine Tree) are trained on historical data. The data set was divided into two segments, with 80% allocated for training and the rest 20% for testing purposes to identify patterns and predict which employees are likely to leave the organization. By doing so, companies can take proactive measures to retain their employees and reduce the costs of hiring and training new ones. Using AI to detect employee churn can potentially provide significant benefits for companies, including improved retention rates, increased productivity, and reduced costs. Overall, using AI to detect employee churn is a promising solution that can help companies retain their employees and achieve their business goals.
At present, my country's electric power enterprises are moving towards the stage of informatization and intelligent development, but there are still many problems in the process of electric power engineering const...
At present, my country's electric power enterprises are moving towards the stage of informatization and intelligent development, but there are still many problems in the process of electric power engineering construction management, such as the large amount of engineering construction business information, untimely processing, and lack of system in the process of electric power engineering construction. Management, etc. are common problems. How to effectively deal with the information of all aspects of the engineering construction project and make each department complete its own project management work is a key problem to be solved urgently for the managers of electric power enterprises. In this regard, this paper designs a power engineering construction management information system, introduces the decision tree algorithm of data mining technology to design the functional modules of the system, and builds a data warehouse on the basis of data mining technology. This paper uses the LoadRunner test tool to test the performance of the system to form a system evaluation and analysis report, and then realize the information management of the power engineering project by the system administrator through the login module.
Recently, urban rail transportation is constantly developing to intelligent urban rail based on the Internet of Things, artificial intelligence, and high-speed communication. Long Term Evolution for Urban Rail Transpo...
详细信息
Electrocardiography(ECG) is a non-invasive tool used to identify the cardiovascular diseases. ECG classification studies have been concerned and made progress well. However, the problems about categories imbalance and...
详细信息
Electrocardiography(ECG) is a non-invasive tool used to identify the cardiovascular diseases. ECG classification studies have been concerned and made progress well. However, the problems about categories imbalance and absence of labelled clinic data are still dramatically hindered research development. Recently, generative models have been verified as a possible way to handle the data scarcity issues. For ECG synthesis, to the best of our knowledge as the reason of time sequences and multiple labels constraints, no model can generate ECG corresponding to clinic *** this paper, we present a novel multi-label conditional generative adversarial network, named MLCGAN. To synthesise reasonable long-term multi-lead data, multi-label mixing module is devised to combine with our improved WaveGAN. Moreover, the sampling strategy based on multilabels distribution is proposed. Comprehensive experiments demonstrate that MLCGAN can generate ECG data satisfied the clinic diagnose requirement and improve the performance of RestNet based ECG classifier.
It is becoming more and more important for healthcare providers to protect the integrity and security of sensitive medical data as they use cloud computing for dataprocessing and storage. This work explores the field...
It is becoming more and more important for healthcare providers to protect the integrity and security of sensitive medical data as they use cloud computing for dataprocessing and storage. This work explores the field of machine learning algorithms that are secure and privacy-preserving when applied to healthcare information in cloud environments. We investigate sophisticated cryptography, federated learning, and differentiating privacy techniques using an interpretive philosophy and a method based on deduction. Our results highlight the computational expense associated with cryptographic protocols, while also revealing their nuanced performance and potential for enabling secure calculations. Federated learning is shown to be effective in collaborative model training, providing a workable approach to privacy-preserving data analysis over-dispersed healthcare datasets. Differential privacy systems require careful parameter calibration because they demonstrate a delicate balance between data value and privacy preservation.
暂无评论