Educational Data Mining Techniques for Student Performance Prediction: Method Review and Comparison Analysis

Student performance prediction (SPP) aims to evaluate the grade that a student will reach before enrolling in a course or taking an exam. This prediction problem is a kernel task toward personalized education and has attracted increasing attention in the field of artificial intelligence and educational data mining (EDM). This paper provides a systematic review of the SPP study from the perspective of machine learning and data mining. This review partitions SPP into five stages, i.e., data collection, problem formalization, model, prediction, and application. To have an intuition on these involved methods, we conducted experiments on a data set from our institute and a public data set. Our educational dataset composed of 1,325 students, and 832 courses was collected from the information system, which represents a typical higher education in China. With the experimental results, discussions on current shortcomings and interesting future works are finally summarized from data collections to practices. This work provides developments and challenges in the study task of SPP and facilitates the progress of personalized education.

Direct Position Analysis of a Particular Translational 3-URU Manipulator

Direct position analysis (DPA) of parallel manipulators (PMs) is in general difficult to solve. Over on PMs' topology, DPA complexity depends on the choice of the actuated joints. From an analytic point of view, the system of algebraic equations that one must solve to implement PMs' DPA is usually expressible in an apparently simple form, but such a form does not allow an analytic solution and even the problem formalization is relevant in PMs' DPAs. The ample literature on the DPA of Stewart platforms well document this point. This paper addresses the DPA of a particular translational PM of 3-URU type, which has the actuators on the frame while the actuated joints are not adjacent to the frame. The problem formulation brings to a closure-equation system consisting of three irrational equations in three unknowns. Such a system is transformed into an algebraic system of four quadratic equations in four unknowns that yields a univariate irrational equation in one of the four unknowns and three explicit expressions of the remaining three unknowns. Then, an algorithm is proposed which is able to find only the real solutions of the DPA. The proposed solution technique can be applied to other DPAs reducible to a similar system of irrational equations and, as far as this author is aware, is novel. Keywords: Kinematics, Position Analysis, Parallel Manipulators, Lower Mobility, Translational Manipulators

Recommendation system for finding improved coworking area based on intelligent information technologies

Purpose The purpose of this study is to make the implementation of a recommended Web service that allows one to formalize the search for a suitable coworking according to individual preferences as a decision-making task, as well as find a coworking area in an optimized setting for both the individual employee and those who carry out collective professional activities from a large number of alternatives in a shorter time. Design/methodology/approach In the implemented system of each place category in coworking areas, a search will be carried out according to formalized parameters and with an individual approach. To find the set of the required services of the coworking zone, the target functions of maximizing the priority of the place and minimizing the cost are determined, between which the user can set the ratio. As a constraint, the general fund of financial expenses for the time to reach the zone from different locations is used. The results of problem formalization are presented in the form of a mathematical model. Findings The use of a problem-oriented solution can significantly reduce the laboriousness of finding a suitable workspace. Originality/value The development of coworking zone practices contributes to the development of a professional infrastructure of the city and minimizes the cost of equipping each enterprise with additional tools, as well as manages labor resources and tracks trends of both professional and novice workers’ needs.

MODELING AS A SCIENTIFIC TOOL FOR SUBSTANTIATION OF MANAGEMENT DECISIONS IN OPERATIONAL ACTIVITIES OF TRANSPORT ENTERPRISES

On the basis of analysis of existing approaches to the process of decision making, in this article the procedure of taking optimal operational decisions is proposed, which describes in detail all of its aspects and features related to the specifics of the operational activities of transport enterprises. In this procedure the basic steps are those directly related to the modeling: formulation of the problem (formalization of the original problem), construction of the model, its solution, credibility and adequacy check, restoration (or adjustment) of the model. The object of the research is decision-making process in the operational management of transport enterprises. The purpose of the research is to develop a procedure for the process of making optimal operational decisions based on existing approaches to the decision-making process, using modeling as a scientific tool to substantiate them. The research method is methods of system analysis and modeling. It has been discovered that the need to reduce the subjectivity of the process of making important decisions in the operational activities of transport enterprises and increase its scientific validity is especially relevant today, in the face of threats and uncertainty about the external environment of the organization. All methods of rational decision-making are based on models, which, in turn, are scientific tools. Modeling creates a serious informational and methodological basis for structural analysis of decisions needed to improve the management process for operational managers and hence - to increase the level of management in general, because it makes them more systematic, and the tools used during this help them be more rational. The results of the article can be implemented during making complex and important management decisions in the operational activities of both transport enterprises and other business entities of various activities, regardless of the organizational and legal form and ownership. KEY WORDS: MODELING METHOD, MODELING, MODEL, TRANSPORT ENTERPRISE, OPERATIONAL ACTIVITY, OPERATIONS MANAGER, MANAGEMENT DECISION.

Risk Assessment of Innovative Projects Implementation in Enterprises Using Artificial Neural Networks

The purpose of this paper is to shed new light on the issue of risk assessment in implementing innovative projects. Based on the ideas of George Kleiner and artificial neural network tools, this paper interprets the possibility of completing successful innovation projects in terms of risk management. The argument is buttressed with a case study of a set of Russian enterprises implementing innovative projects. Successful completion of an innovation project depends on a number of risk factors identified at the project start. The identified set of risk factors should include both innovative risk factors and non-innovative risk factors. This fact was established during the cluster analysis of the available data. The paper excludes from consideration the anti-risk management impact and does not take into account the weights of various risk factors in the problem formalization. The practical application of the results of the study is decision makers’ quest to strike a visual interpretation of the final data with a small number of possible scenarios that differ significantly from each other. This research contributes significantly to the literature on the risk assessment model of innovative projects. The failure of managers to balance the assessment of innovative risk factors and non- innovative risk factors is exposed as the root cause of the unsuccessful completion of innovative projects.

Routing Driverless Transport Vehicles in Car Assembly with Answer Set Programming

Automated storage and retrieval systems are principal components of modern production and warehouse facilities. In particular, automated guided vehicles nowadays substitute human-operated pallet trucks in transporting production materials between storage locations and assembly stations. While low-level control systems take care of navigating such driverless vehicles along programmed routes and avoid collisions even under unforeseen circumstances, in the common case of multiple vehicles sharing the same operation area, the problem remains how to set up routes such that a collection of transport tasks is accomplished most effectively. We address this prevalent problem in the context of car assembly at Mercedes-Benz Ludwigsfelde GmbH, a large-scale producer of commercial vehicles, where routes for automated guided vehicles used in the production process have traditionally been hand-coded by human engineers. Such ad-hoc methods may suffice as long as a running production process remains in place, while any change in the factory layout or production targets necessitates tedious manual reconfiguration, not to mention the missing portability between different production plants. Unlike this, we propose a declarative approach based on Answer Set Programming to optimize the routes taken by automated guided vehicles for accomplishing transport tasks. The advantages include a transparent and executable problem formalization, provable optimality of routes relative to objective criteria, as well as elaboration tolerance towards particular factory layouts and production targets. Moreover, we demonstrate that our approach is efficient enough to deal with the transport tasks evolving in realistic production processes at the car factory of Mercedes-Benz Ludwigsfelde GmbH.