Figure 6 - uploaded by Trung Hieu Tran
Content may be subject to copyright.
Source publication
Machine learning and data mining are research areas of computer science whose quick development is due to the advances in data analysis research, growth in the database industry and the resulting market needs for methods that are capable of extracting valuable knowledge from large data stores. A vast amount of research work has been done in the mul...
Contexts in source publication
Context 1
... The defined number of iterations has been achieved. The demonstration of the algorimthi is described as in Figure 6. K-Means has the advantage that it's pretty fast, as all we are really doing is computing the distances between points and group centers; very few computations. ...
Similar publications
Machine learning and data mining are research areas of computer science whose quick development is due to the advances in data analysis research, growth in the database industry and the resulting market needs for methods that are capable of extracting valuable knowledge from large data stores. A vast amount of research work has been done in the mul...
Citations
... Examples of Deep Learning models include ANN [26,75,90,92,139,[145][146][147][148][149], and perceptrons [141]. Modern versions of ANN, known as Deep Learning, such as Convolutional Neural Network (CNN) [140], have been established in which larger neural networkswith many hidden layersare extensively utilized [150]. For convenience and reference, a list of the abbreviations and definitions of the reviewed algorithms have been summarized in Table 1. ...
Machine Learning (ML) appears to have become the main and foremost approach to both tackle the hurdles and exploit the opportunities of The Information Age. We present our analytical review of the past years applications of the developed ML models in Materials Science. We begin our analysis by highlighting the similarities and the basic difference between Machine Learning and Screening approaches, and focus our work on direct ML applications only. The general ML procedure to develop a successful ML model for materials is illustrated and explained. We also present charts and tables summarizing the relevant literature works into categories based on ML techniques, materials classes, and materials predicted properties. Details and reasons of the most successful applications are explored and discussed based on sample cases. The information, data, and suggested guidelines in this work would be useful to interested researchers in the field of Materials Science.
... Text mining has been also utilized in code mining of other fields such as software engineer. Those techniques follows a data-driven approach to recover names by searching in a large corpus of data (Tran H., 2019) and to understand the code semantic . ...
... Overfitting is the tendency of data mining techniques to generate models which tailor to training data without generalization to previously unseen data (Provost and Fawcett, 2013) Different supervised machine learning algorithms are employed to preform prediction: Decision Tree, Neural Network and knn which were then evaluated and the one which yields highest accuracy level will be chosen to formulate the final model (Reiman., 2018) -Decision Tree: is one of the most widely used and practical supervised machine learning method. It builds models in the tree-like graph, which breaks down data into subsets while at the same time, an associated decision is incrementally built (Tran., 2019). Each node represents an attribute, each brand defines a rule, and each leaf represents an outcome which altogether represents classification rules. ...
... -Naïve Bayes: is a set of supervised learning algorithms based on the assumption of conditional independence over training data set (Tran., 2019). Naïve Bayes works well with a large dataset in a complex context. ...
Social media is seen as a platform where people freely express their opinions about any matter, thus, generating a massive amount of user-generated content. Twitter undoubtedly has held its firm position among all social networking sites with an exponential number of users every year. Many studies were carried out by investigating the power of Twitter data in the health care industry, politics, sports, and music industry. Over the last five years, the music industry has experienced a shift in the way people listen to music since the introduction of online streaming music. Music lovers are prone to interact with their favorite songs and artists through social media, which provides enormous troves of insight not on just individual song and artists but also on how music consumers perceive any song. Therefore, many kinds of research have been carried out to investigate the impact of Twitter on forecasting songs revenue. However, there are only two studies that aimed to explore the predictive power of Twitter to song performance. This paper shed some light on this little-recognized topic by evaluating Twitter data in forecasting song popularity, which is demonstrated via the Billboard Top 100 chart.
The results indicated that while Twitter data can be utilized as a predictor of song popularity, incorporating Twitter and Billboard information (number of weeks the songs presented in the chart) enhance chart prediction than sole Twitter data. Findings of this study are beneficial to the music industry to discover song performance by real-live update trends on social media in order to propose an appropriate strategy for hit and non-hit songs.
Breast Cancer, with an expected 42,780 deaths in the US alone in 2024, is one of the most prevalent types of cancer. The death toll due to breast cancer would be very high if it were to be totaled up globally. Early detection of breast cancer is the only way to decrease the mortality caused by it. In order to diagnose breast cancer, even the most competent and qualified pathologists and radiologists have to examine hundreds of high-resolution images, which is a massive burden on them. Compared to the number of cases, very few experts are available to manage this burden. Additionally, as humans are more prone to mistakes, the likelihood of finding false positive cases is also high. Numerous AI techniques, including machine learning and deep learning, are ideally suited to address these issues, inspiring many researchers to introduce novel computer-aided detection systems.
In this study, we have comprehensively reviewed pre-existing literature aimed at developing computer-aided systems based on using machine learning, deep learning, and vision transformers to identify and classify breast cancer. We have discussed numerous imaging modalities for detecting breast cancer, along with the widely used data pre-processing approaches, machine learning and deep learning models, as well as ensemble learning methods suitable for the task. Popular datasets and their sources are also listed for future referencing. Finally, we have identified a few gaps and addressed potential future research directions with an intent of aiding researchers select approaches tailored to case-specific needs.
