Road traffic accidents (RTA) pose a significant public health threat worldwide, leading to considerable loss of life and economic burdens. This is particularly acute in developing countries like Bangladesh. Building reliable models to forecast crash outcomes is crucial for implementing effective preventive measures. To aid in developing targeted safety interventions, this study presents a machine learning-based approach for classifying fatal and non-fatal road accident outcomes using data from the Dhaka metropolitan traffic crash database from 2017 to 2022. Our framework utilizes a range of machine learning Classification algorithms, comprising Logistic Regression, Support Vector Machines, Naive Bayes, Random Forest, Decision Tree, Gradient Boosting, LightGBM, and Artificial Neural Network. We prioritize model interpretability by employing the SHAP (SHapley Additive exPlanations) method, which elucidates the key factors influencing accident fatality. Our results demonstrate that LightGBM outperforms other models, achieving a ROC-AUC score of 0.72. The global, local, and feature dependency analyses are conducted to acquire deeper insights into the behavior of the model. SHAP analysis reveals that casualty class, time of accident, location, vehicle type, and road type play pivotal roles in determining fatality risk. These findings offer valuable insights for policymakers and road safety practitioners in developing countries, enabling the implementation of evidence-based strategies to reduce traffic crash fatalities.

While the sole purpose of undergraduate education is not to prepare the students for the industry, it is certainly one of its important objectives. In this work, we investigate how well the Bangladeshi software and IT-related undergraduate education prepares the students for the software industry. We conducted semi-structured interviews of twenty practitioners from the Bangladeshi software industry. During the interviews, these practitioners provided commentary on where they believe the undergraduate education system falls short, and provided their suggestions for improvement. Based on the themes discovered from the interviews, we created a survey where more than two hundred practitioners participated. The results of our work suggest that most of the practitioners believe that, while some aspects of the undergraduate education are fine, the undergraduate education system leaves its graduates largely unprepared for the software industry. In this paper, we summarize and present the practitioners' opinions on some key areas including but not limited to updating of syllabi, internships as part of the curricula, the nature, length and evaluation process of undergraduate projects, pedagogical issues, and academic practices.

Code smell is a sign of design and development flaws in a software system which reduces the reusability and maintainability of the system. Refactoring is a continuous practice of eliminating code smells from the source code. A God Class is one of the most common code smells where too many responsibilities are defined in a single class. God Classes reduce the quality of a system by increasing coupling and decreasing cohesion. In this paper, we propose an approach for extracting a God Class into new classes by increasing class cohesion. For this, both structural and semantic relationship between methods in a class are analyzed, and strongly related methods are clustered and suggested to be in the same class. We assessed the proposed approach on fifteen real God Classes from two well-known open source systems and it is shown that the cohesion among the classes is increased after refactoring. A comparative result of our approach with a similar existing approach is presented and it is found that our approach provides better results for almost all the experimented God Classes.

During the gradual process of software evolution, errors appear in different components of a software system.These errors are later on fixed by developers as part of corrective maintenance activities.However, if errors appear continuously from a particular component, that may indicate design flaws or code smells.Maintenance cost will greatly reduce if design flaws are treated as early as possible.To find out such flaws it may require time-consuming manual inspections.This paper tries to find out such components using the information of change coupled cluster of files or Java classes at fix-inducing changes.In this proposed approach, information (like class, method, parameter of method and variable names) from change coupled relation of a class at Fix-Inducing Changes (FICs) are used to provide information about erroneous components.Then the error history, of software components, is found by using cosine similarity of information from change coupled cluster of classes found in FICs to see with the architectural information found from authenticated sources.Finally, the error history of components is shown as the percentage of change coupled cluster of a class found in FICs of each 100 commits in the version control system.

We introduce a novel ensemble learning framework for supervised classification. Our proposed framework, mixed bagging, is a form of bootstrap aggregating (bagging) in which the sampling process takes into account the classification hardness of the training instances. The classification hardness, or simply hardness, of an instance is defined as the probability that the instance will be misclassified by a classification model built from the remaining instances in the training set. We incorporate instance hardness into the bagging process by varying the sampling probability of each instance based on its estimated hardness. Bootstraps of differing hardness can be created in this way by over-representing, under-representing and equally representing harder instances. This results in a diverse committee of classifiers induced from the bootstraps, whose individual outputs can be aggregated to achieve a final class prediction. We propose two versions of mixed bagging – one where the bootstraps are grouped as easy, regular or hard, with all bootstraps in one group having the same hardness; and the other where the hardness of bootstraps change gradually from one iteration to the next. We have tested our system on 47 publicly available binary classification problems using C4.5 Decision Trees of varying depth as base learners. We find that the proposed mixed bagging methods perform better than traditional bagging and weighted bagging (wagging) regardless of the base learner. The proposed method also outperforms AdaBoost when the base learner consists of deeper decision trees. We examine the results of mixed bagging in terms of bias-variance decomposition and find that mixed bagging is better than AdaBoost at reducing variance and better than traditional bagging at reducing inductive bias.