Is Deep Learning on Tabular Data Enough? An Assessment

Fayaz, Sheikh Amir; Zaman, Majid; Kaul, Sameer; Butt, Muheet Ahmed

doi:10.14569/ijacsa.2022.0130454

Cited by 23 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…XGBoost is a novel tree-based algorithm for sparse data processing that provides the gradient-boosted decision tree, which is widely recognized in data mining challenges and tasks ( 40 , 41 ). Some studies ( 42 , 43 ) have indicated that XGBoost performs better than do deep learning methods in tabular data analysis. The optimal sample:feature ratio is 10, which may be a universal conclusion in radiomics research.…”

Section: Discussionmentioning

confidence: 99%

Prognostic prediction of left ventricular myocardial noncompaction using machine learning and cardiac magnetic resonance radiomics

Han,

Jiang,

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background Although there are many studies on the prognostic factors of left ventricular myocardial noncompaction (LVNC), the determinants are varied and not entirely consistent. This study aimed to build predictive models using radiomics features and machine learning to predict major adverse cardiovascular events (MACEs) in patients with LVNC. Methods In total, 96 patients with LVNC were included and randomly divided into training and test cohorts. A total of 105 cine cardiac magnetic resonance (CMR)-derived radiomics features and 35 clinical characteristics were extracted. Five different oversampling algorithms were compared for selection of the optimal imbalanced processing. Feature importance was assessed with extreme gradient boosting (XGBoost). We compared the performance of 5 machine learning classification methods with different sample:feature ratios to determine the optimal hybrid classification strategy. Subsequently, radiomics, clinical, and combined radiomics-clinical models were developed and compared. Results The machine learning pipeline included an adaptive synthetic (ADASYN) algorithm for imbalanced processing, XGBoost feature selection with a sample:feature ratio of 10, and support vector machine (SVM) modeling. The areas under the receiver operating characteristic curves (AUCs) of the radiomics model, clinical model, and combined model in the validation cohort were 0.87 (sensitivity 83.33%, specificity 64.29%), 0.65 (sensitivity 16.67%, specificity 78.57%), and 0.92 (specificity 33.33%, sensitivity 100.00%), respectively. The radiomics model performed similarly to the clinical and combined models (P=0.124 and P=0.621, respectively). The performance of the combined model was significantly better than that of the clinical model (P=0.003). Conclusions The machine learning-based cine CMR radiomics model performed well at predicting MACEs in patients with LVNC. Adding radiomics features offered incremental prognostic value over clinical factors alone.

show abstract

Section: Discussionmentioning

confidence: 99%

Prognostic prediction of left ventricular myocardial noncompaction using machine learning and cardiac magnetic resonance radiomics

Han,

Jiang,

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

show abstract

“…As a result, we conducted an experimental investigation of the M5 mode tree on rainfall data to see how accurate and practicable the model is [19][20][21]. This research will assist us in determining why this algorithm is not commonly used, as well as evaluating the performance of M5 mode tree on different types of data such as agricultural, health, and academic data [22,23].…”

Section: Literature Reviewmentioning

confidence: 99%

How M5 Model Trees (M5-MT) on Continuous Data Are Used in Rainfall Prediction: An Experimental Evaluation

Fayaz¹,

Zaman²,

Kaul³

et al. 2022

RIA

Self Cite

View full text Add to dashboard Cite

When using machine learning to predict a class with a continuous numeric value, there are several issues. Only a few machine-learning approaches are capable of doing so, but it remains one of the most difficult jobs to do. In this paper, we show how to use the M5 Model Tree, an approach that can handle continuous numeric data. This method is a stepwise procedure that employs linear functions at the leaf nodes of any created decision tree inducer (such as CART). These M5 model trees provide basic practical formulas such as standard deviation (SD), standard deviation reduction (SDR), cost-complexity pruning (CCP), and so on, which may be simply applied to different benchmark data by another user. This study examines the M5 Model Tree algorithm's capabilities for analysing rainfall data in the Kashmir portion of India's Union Territory of Jammu & Kashmir. One of the best suited models was the M5 model tree, which was built using (70–30) percent training and test ratios, respectively, and predicted an RMSE of 2.593, an MAE of 1.68, and a correlation coefficient (R2) of 0.478. Furthermore, M5 model trees produce models with a minimal number of trails, requiring less computing effort and making them more practical to use.

show abstract

“…The following are some of the challenges [41][42][43] faced while using data mining techniques to study the University's big data: The data at the university is heterogeneous, lacking in atomicity, and the main issue is that the data is inconsistent and redundant.…”

Section: Resolution and Challenges: A Big Data Analytics Approachmentioning

confidence: 99%

Big Data in Academia: A Proposed Framework for Improving Students Performance

Banday¹,

Zaman²,

Quadri³

et al. 2022

RIA

View full text Add to dashboard Cite

The way people learn has radically changed as a result of information technology. As an informal method of learning, fragmented learning has become a popular way to learn new technology and expertise. Academic organizations generate a large amount of heterogeneous data, and academic leaders want to make the most of it by analyzing the large amount of data in order to make better decisions. The volume isn't the only issue; the organization's data structure (structured, semi structured, and unstructured) adds to the complexity of academic work and decision-making on a daily basis. As big data has become more prevalent in educational settings, new data-driven techniques to enhance informed decision-making and efforts to improve educational efficacy have emerged. Traditional data sources and approaches were previously too expensive to obtain with digital traces of student behaviour, which offer more scalable and finer-grained comprehension and support of learning processes. This study provides a fragmented learning solution for students in a data environment that can suggest subjects to them based on their geographical location, gender, and district of residence, among other factors. This suggested framework is expected to play a key role in directing the development of a society that values lifelong learning.

show abstract

Is Deep Learning on Tabular Data Enough? An Assessment

Cited by 23 publications

References 0 publications

Prognostic prediction of left ventricular myocardial noncompaction using machine learning and cardiac magnetic resonance radiomics

Prognostic prediction of left ventricular myocardial noncompaction using machine learning and cardiac magnetic resonance radiomics

How M5 Model Trees (M5-MT) on Continuous Data Are Used in Rainfall Prediction: An Experimental Evaluation

Big Data in Academia: A Proposed Framework for Improving Students Performance

Contact Info

Product

Resources

About