Recursos

In healthcare, developing high procedural skill levels through training is a key factor for obtaining good clinical results on surgical pro- cedures. Providing feedback to each student tailored to how the student has performed the procedure each time, improves the effectiveness of the training. Current state-of-the-art feedback relies on Checklists and Global Rating Scales to indicate whether all process steps have been performed and the quality of each execution step. However, there is a process perspective not successfully captured by those instruments, e.g., steps performed but in an undesired order, part of the process repeated an unnecessary number of times, or excessive transition time between steps. In this work, we propose a novel use of process mining techniques to effectively identify desired and undesired process patterns regarding rework, order, and performance, in order to complement the tailored feed- back of surgical procedures using a process perspective. The approach has been effectively applied to analyze a real Central Venous Catheter installation training case. In the future, it is necessary to measure the actual impact of feedback on learning.

The BPI Challenge 2017 provides a real-life event log com- posed by loan applications and offers, generated by a bank to analyze the data and improve their processes. This paper analyzes the through- put times of the process, in particular the difference between the time spent in the company’s systems waiting for processing by a user and the time spent waiting for an input from the applicant. Moreover, we evaluated the influence of the frequency of incompleteness on the final outcome and if the quantity of offers requested by the customer matters. Other interesting trends are analyzed, such as efficient use of resources, business rules compliance and identification of behavioral patterns at dif- ferent times of the day. Results show that a lack of customer requests for completion does not improve the credit approval rate and that this rate decreases when there are more offers. Also, the more the users engage in the case, the greater the approval rate, but the throughput times get longer as well.

Dynamically allocating the most appropriate resource to execute the different activities of a business process is an important challenge in business process management. An ineffective allocation may lead to an inadequate resources usage, higher costs, or a poor process performance. Different approaches have been used to solve this challenge: data mining techniques, probabilistic allocation, or even manual allocation. However, there is a need for methods that support resource allocation based on multi-factor criteria. We propose a framework for recommend- ing resource allocation based on Process Mining, that does the recommendation at sub-process level, instead of activity-level. We introduce a resource process cube that provides a flexible, extensible and fine-grained mechanism to abstract historical information about past process executions from process event logs. Then, several metrics are computed over the cube, considering different criteria: fitting between resources expertise and the expertise required to perform an activity, past performance (frequency, duration, quality and cost), and resources workload. These metrics are combined to obtain a final recommendation ranking based on the BPA algorithm. The approach is applied to a help desk scenario to demonstrate its usefulness.

This article describes the process of implementing a business process management supported by a service-oriented architecture from a business perspective. Also, it is to suggest how you can do to effectively balance the use of BPM and SOA as an entity differentiator for modern companies that drive the achievement of agile and flexible processes in their businesses.

In the context of the International Business Process Challenge (BPIC, 2018) which is centered this year on the European Agri- cultural Guarantee Fund process, this essay present the results of the study of several questions made by the authors of this document. The first inquiry was to determine the differences between the cases in which the Payment Application was approved in the first attempt, versus the cases with a rejected Payment Application document, showing a loop path for rejected cases and an analysis with suggestions to improve the main process. The second question is related to the differences that can be perceived between the longest cases and the shortest, and it was found a ”trigger” that can be used to determine whether or not a particular case will last longer than usual. The third question was asked in order to determine if there are patterns in the processes that could help pre- dict which cases will be reopened. After they are reopened, the research group also study whether they behave similarly to the rest of the cases, where they found that this does not happen in a lot of cases. In the fourth question were determined the differences between the processes of the rejected and the approved cases, where it was found that perhaps it is possible to determine sooner whether a case is going to be rejected or not.

This paper analyses a loan application process of a Dutch Financial Institute proposed by the BPIC Challenge 2017 using process mining tools and techniques. Several filters and performance and organizational analysis are executed in order to observe underlying patterns that may explain some of the bottlenecks of the process, time spent on certain activities and their acceptance rate. Also, we proposed a recommender system to assist client profiling. Our results also include observations regarding to customer communication.

Informal caregivers take care of someone (usually a close family member) who suffers from a chronic illness. In this stressful situation, caregivers have a high risk of depression or loneliness, because their social network is weakened. Most existing proposals focus on helping caregivers fulfill caregiving tasks, instead of providing support for their mental wellbeing (e.g. identifying early stages of social isolation). We present a prototype ambient interface, called EmoTree, that makes communication frequency tangible by using a metaphor of a tree, and investigate user perception and motivation of use. People found Emotree to be interesting and enjoyable (78%), and useful (54%) unless the user does not suffer some type of problem (69%). Our preliminary results show the interface is easy to use and has an adequate representation of communication frequency. Our next step will make a second assessment with informal caregivers in their real context.

Nowadays, business corporations are immersed in a competitive world, in which there is current need to revise and renovate traditional business models. Information technologies offer the possibi- lity of defining new business strategies through the use of technology innovation and all of its recent breakthroughs. The virtualization of IT recourses shelters the creation of an IT platform composed of replicates of actual computers machines built on a software base. The objective of this article is to present a panoramic view of the main features, types, uses, and current trends offered by the advantages of this technology.

Dynamic resource allocation is considered a major challenge in the context of business process management. At the operational level, flexible methods that support resource allocation and which consider different criteria at run-time are required. It is also important that these methods are able to support multiple allocations in a simultaneous manner. In this paper, we present a framework based on multi-factor criteria that proposes a recommender system which is capable of recommending the most suitable resources for executing a range of different activities, while also considering individual requests or requests made in blocks. To evaluate the proposed framework, a number of experiments were conducted using different test scenarios. These scenarios provide evidence that our approach based on multi-factor criteria successfully allocates the most suitable resources for executing a process in real and flexible environments. In order to demonstrate this assertion, we use a help-desk process as a real case study. 

The BPIC Challenge 2017 provides an event log based on a real financial entity that represents the loan approval process triggered by the clients’ applications submission. The mentioned log consists of 31,509 cases, there are 4,047 variants and from the whole process are recognized 26 activities. The analysis was done using process mining tools and spreadsheet manipulation. The challenge proposed four questions that would allow us to explore certain subsets of the data and analyze them. The first question is about the throughput times of the process; the second question concerns about the conversion rate of multiple and single offer cases; the third question try to discover the system users influence in the final outcome of its clients application; and the fourth questions is about the behavior of clients whose offers are cancelled. We found that clients were slower than bank’s workers and this happens in spite of the type of case. Also, the system user - client affects the final status of a given offer and that the value of this type of interaction can be quantified. Besides, the conversion rate is similar between single and multiple offers. We proposed an inactivity model to make predictions about the possible outcomes given certain characteristic of each case. Finally, we give some recommendations to handle these situations.