Class imbalance exists in many data domains, posing numerous challenges to the data research community. Medical datasets, in most cases are predominantly imbalanced in nature. Through tackling multi-class issues, most researchers preferred the conventional method of decomposing it into binary classes for a more convenient solution. This method is not applicable for solving sensitive and crucial domains, such as medical data. Classifying medical datasets require all the classes to retain their form and maintain clinical validity. In this article, we develop a rebalancing framework for the multi-classification of imbalanced medical data using SCUT (SMOTE and Cluster-based Undersampling Technique) to rebalance the imbalanced class distribution, a feature selection method using a combination of SHapley Additive exPlanations (SHAP) and Recursive Feature Elimination (RFE), and DES-MI (Dynamic Ensemble Selection for multi-class) for improved multi classification performance. There are two novelties that contributes to the performance of our framework: improvised SCUT by implementing two clustering algorithms, and our proposed pool classifier selection for DES-MI. The performance of the proposed framework was compared with other state-of-the-art imbalanced framework using eight imbalanced datasets, each with varying degrees of imbalance. The experimental results indicate that our proposed framework performed better with average performance of 81.77%, 73.57%, and 75.87% in terms of Macro Average accuracy, extended G-mean, and Macro Average AUC, respectively. Our framework drastically increases the overall performances, owing to its ability to significantly handles the multi-class imbalance problem.
Research based on datasets needs to determine the quality of the data that form the basis of the results. To facilitate this type of research, the meaning of the data needs to be interpreted correctly. A dataset essentially contains data and metadata. Data are often misinterpreted due to insufficient metadata, which causes quality issues to be associated with the datasets, such as failure to clearly identify the entity being measured and inability to clarify how the measurements were generated. The goal of this study was to determine a useful way to evaluate the quality of datasets. We developed a quality assessment process that includes four steps: assessing the datasets model, identifying the data quality issues, evaluating the metadata, and preparing the assessment report. We introduced formal definitions of data quality issues to identify the quality issues, as well as an evaluation scale to evaluate the quality of the metadata in datasets. We applied the quality assessment process to 92 existing datasets from real data repositories and found a number of common data quality issues in these datasets, such as duplicate, incorrect and missing data. We also found 70 datasets containing insufficient metadata for entity and metrics. Our quality assessment process can be used to determine datasets that might carry risks of data misinterpretation because of the absence of metadata. The process also allows researchers to draw conclusions about whether a dataset has sufficient metadata to support correct interpretation for analysis in empirical research.
10 April 2025 in Babylonian Journal of Mechanical Engineering
Real-time process monitoring is essential for achieving consistent part quality in Laser Powder Bed Fusion (LPBF), yet robust and practical defect prediction frameworks remain underdeveloped. This study presents a machine learning-based approach for predicting unstable melt pool conditions, leveraging an open dataset of melt pool variability measurements from Ti-6Al-4V builds on an EOS M290 system. The framework utilizes fundamental process parameters—laser velocity, power, scan orientation, and track location—combined with statistical melt pool geometry features to train a Random Forest classifier. The model achieved an accuracy of 99.79% in distinguishing between stable and unstable melt pool states, with balanced sensitivity and specificity. Analysis of defect trends across the process parameter space revealed that higher scan velocities and certain orientations significantly increase defect likelihood. The results confirm that interpretable, computationally efficient machine learning models can provide robust real-time defect prediction using features already accessible on commercial LPBF platforms. The framework offers a scalable and industry-relevant pathway toward enhanced quality assurance in metal additive manufacturing, supporting the advancement of intelligent, closed-loop LPBF process control.
Most of the current project management software's are utilizing resources on developing areas in software projects. This is considerably essential in view of the meaningful impact towards time and cost-effective development. One of the major areas is the fault proneness prediction, which is used to find out the impact areas by using several approaches, techniques and applications. Software fault proneness application is an application based on computer aided approach to predict the probability that the software contains faults. The application will uses object oriented metrics and count metrics values from open source software as input values to the genetic algorithm for generation of the rules to classify the software modules in the categories of Faulty and Non Faulty modules. At the end of the process, the result will be visualized using genetic algorithm applet, bar and pie chart. This paper will discussed the detail design of software fault proneness application by using genetic algorithm based on the object oriented approach and will be presented using the Unified Modeling Language (UML). The aim of the proposed design is to develop an automated tool for software development group to discover the most likely software modules to be high problematic in the future.
Background: The quality of data sets used in software engineering research is of the utmost importance. To ensure credibility of results obtained from use of data sets, the quality of the data must be examined. Objective: This study provides an overview of recent research(2008-2012) involving data quality in software engineering datasets, with the goal of generally understanding what research there is that addresses data quality, and in particular to determine to what degree researchers have addressed any data quality issues in order to evaluate the trustworthiness of their results. Method: We performed a systematic mapping study to investigate treatment of data quality issues in software engineering research. A total of 64 papers published from 2008 to 2012explicitly address issues with the quality of data and use software engineering data sets. These studies were classified according to the data quality topic, data set and data quality problem. Results: We found only 31 studies gave serious consideration for how the quality of the data affected their results. We observed that there is a lack of clear and consistent terminology regarding data quality, especially with respect to the kinds of quality problems a data set might have. As a first step to address this problem, we propose a model that describes the lifecycle that research data goes through when used in research. Conclusions: The results suggest that researchers should give more attention to the quality of data sets in order to produce trustworthy data for reliable empirical research, and that the research community needs to better understand and communicate issues with data quality.
1 February 2021 in Bulletin of Electrical Engineering and Informatics