Applications of Data Mining in Computer Decision Support System and Other Related Aspects

Abnormal passenger behavior in rail transit has become a top priority, as it affects operational safety. Passenger travel time is the main basis for identifying abnormal behavior while considering the flexibility of travel time. Currently, the main method is to use absolute threshold discrimination based on the distribution of travel time. However, there is a problem of missing abnormal passenger behavior due to the large difference in travel time between the Origin-Destinations (ODs). Therefore, this paper proposes a method of setting corresponding thresholds for each OD. By analyzing the percentile curves of the overall and individual OD pairs, it was found that the turning point of the curve had a significant feature, and the difference between the two sides of the curve was obvious. This paper proposes a bilateral fitting method, and the results show that this method can calculate the relative threshold for different OD pairs. The significant advantages of this method are its low cost and wide coverage. Full article

Most research on fairness in Machine Learning assumes the relationship between fairness and accuracy to be a trade-off, with an increase in fairness leading to an unavoidable loss of accuracy. In this study, several approaches for fair Machine Learning are studied to experimentally analyze the relationship between accuracy and group fairness. The results indicated that group fairness and accuracy may even benefit each other, which emphasizes the importance of selecting appropriate measures for performance evaluation. This work provides a foundation for further studies on the adequate objectives of Machine Learning in the context of fair automated decision making. Full article

As the degree of elders’ social activity and self-care ability depreciates, the potential risk for elderly people who live independently increases. The development of assistive services such as smart homes could likely provide them with a safer living environment. These systems collect sensor data to monitor residents’ daily activities and provide assistance services accordingly. In order to do so, a smart home must understand its residents’ daily activities and identify their periodic behavioral daily routine accordingly. However, existing solutions mainly focus on the temporal feature of daily activities and require prior labeling of where sensors are geographically deployed. In this study, we extract implicit spatial information from hidden correlations between sensors deployed in the environment and present a concept of virtual locations that establishes an abstract spatial representation of the physical living space so that prior labeling of the actual location of the sensors is not required. To demonstrate the viability of this concept, an unsupervised periodic behavioral routine discovery method that does not require any predefined location-specific sensor data for a smart home environment is proposed. The experimental results show that with the help of virtual location, the proposed method achieves high accuracy in activity discovery and significantly reduces the computation time required to complete the task relative to a system without virtual location. Furthermore, the result of simulated anomaly detection also shows that the periodic behavioral routine discovery system is more tolerant to differences in the way routines are performed. Full article

Student success rate is a significant indicator of the quality of the educational services offered at higher education institutions (HEIs). It allows students to make their plans to achieve the set goals and helps teachers to identify the at-risk students and make timely interventions. University decision-makers need reliable data on student success rates to formulate specific and coherent decisions to improve students’ academic performance. In recent years, EDM has become an effective tool for exploring data from student activities to predict their final grades. This study presents a case study for predicting the students’ final grades based on their activities in Moodle Learning Management System (LMS) and attendance in online lectures conducted via Zoom by applying statistical and machine learning techniques. The data set consists of the final grades for 105 students who study Object-Oriented Programming at the University of Plovdiv during the 2021–2022 year, data for their activities in the online course (7057 records), and attendance to lectures (738). The predictions are based on 46 attributes. The Chi-square test is utilized to assess the association between students’ final grades and event context (lectures, source code, exercise, and assignment) and the relationships between attendance at lectures and final results. The logistic regression model is utilized to assess the actual impact of event context on “Fail” students in a multivariate setup. Four machine learning algorithms (Random Forest, XGBoost, KNN, and SVM) are applied using 70% of training data and 30% of test data to predict the students’ final grades. Five-fold cross validation was also utilized. The results show correlations between the students’ final grades and their activity in the online course and between students’ final grades and attendance at lectures. All applied machine learning algorithms performed moderately well predicting the students’ final results, as the Random Forest algorithm obtained the highest prediction accuracy—78%. The findings of the study clearly show that the Random Forest algorithm may be used to predict which students will fail after eight weeks. Such data-driven predictions are significant for teachers and decision-makers and allow them to take measures to reduce the number of failed students and identify which types of learning resources or student activities are better predictors of the student’s academic performance. Full article

The military environment generates a large amount of data of great importance, which makes necessary the use of machine learning for its processing. Its ability to learn and predict possible scenarios by analyzing the huge volume of information generated provides automatic learning and decision support. This paper aims to present a model of a machine learning architecture applied to a military organization, carried out and supported by a bibliometric study applied to an architecture model of a nonmilitary organization. For this purpose, a bibliometric analysis up to the year 2021 was carried out, making a strategic diagram and interpreting the results. The information used has been extracted from one of the main databases widely accepted by the scientific community, ISI WoS. No direct military sources were used. This work is divided into five parts: the study of previous research related to machine learning in the military world; the explanation of our research methodology using the SciMat, Excel and VosViewer tools; the use of this methodology based on data mining, preprocessing, cluster normalization, a strategic diagram and the analysis of its results to investigate machine learning in the military context; based on these results, a conceptual architecture of the practical use of ML in the military context is drawn up; and, finally, we present the conclusions, where we will see the most important areas and the latest advances in machine learning applied, in this case, to a military environment, to analyze a large set of data, providing utility, machine learning and decision support. Full article

As an effective and efficient discriminative learning method, the broad learning system (BLS) has received increasing attention due to its outstanding performance without large computational resources. The standard BLS is derived under the minimum mean square error (MMSE) criterion, while MMSE is with poor performance when dealing with imbalanced data. However, imbalanced data are widely encountered in real-world applications. To address this issue, a novel cost-sensitive BLS algorithm (CS-BLS) is proposed. In the CS-BLS, many variations can be adopted, and CS-BLS with weighted cross-entropy is analyzed in this paper. Weighted penalty factors are used in CS-BLS to constrain the contribution of each sample in different classes. The samples in minor classes are allocated higher weights to increase their contributions. Four different weight calculation methods are adopted to the CS-BLS, and thus, four CS-BLS methods are proposed: Log-CS-BLS, Lin-CS-BLS, Sqr-CS-BLS, and EN-CS-BLS. Experiments based on artificially imbalanced datasets of MNIST and small NORB are firstly conducted and compared with the standard BLS. The results show that the proposed CS-BLS methods have better generalization and robustness than the standard BLS. Then, experiments on a real ultrasound breast image dataset are conducted, and the results demonstrate that the proposed CS-BLS methods are effective in actual medical diagnosis. Full article