Imam Mukhlash

Decision mining for multi choice workflow patterns

Decision mining is combination of process mining and machine learning technique to retrieve information about how an attribute in a business process affects a cases route choice. It identifies decision point by looking for XOR-splits in petri-net workflow model and analyzing rules for each choice based on available attributes using decision tree. Problem emerges when decision mining technique is used on a workflow that does not use either XOR or AND splits, for example OR-split gateway logic. OR-split does not have explicit representation in petri nets and it makes decision mining algorithm cannot find its decision point. Workflow pattern that uses OR-split as its splitting logic is multi choice. Multi choice does not have its own explicit representation in form of petri net and it is problematic to apply decision mining to this workflow pattern. To make multi choice can be analyzed by decision miner some modification needs to be applied to the petri net representation of this pattern. This paper proposes modification of OR-split gateway representation in petri net. The new representation of OR-split uses combination the existing XOR-split and AND-split to make the model easier to be analyzed using decision miner. The proposed modification do not affect the conformance of event log and process model, but will allow each choice branch to be checked by decision miner.

Mining Fuzzy Time Interval Periodic Patterns in Smart Home Data

Basis test paths is a method that uses a graph contains nodes as a representation of codes and the lines as a sequence of code execution steps. Determination of basis test paths can be generated using a Genetic Algorithm, but the drawback was the number of iterations affect the possibility of visibility of the appropriate basis path. When the iteration is less, there is a possibility the paths do not appear all. Conversely, if the iteration is too much, all the paths have appeared in the middle of iteration. This research aims to optimize the performance of Genetic Algorithms for the generation of Basis Test Paths by determining how many iterations level corresponding to the characteristics of the code. Code metrics Node, Edge, VG, NBD, LOC were used as features to determine the number of iterations. J48 classifier was employed as a method to predict the number of iterations. There were 17 methods have selected as a data training, and 16 methods as a data test. The system was able to predict 84.5% of 58 basis paths. Efficiency test results also show that our system was able to seek Basis Paths 35% faster than the old system.A single-fed linearly polarized 2x2 microstrip bow tie array antenna is proposed. The feed network has microstrip line and slot line where microstrip-slot branch circuit is connected in parallel. The feed network of the array is designed using both-sided MIC Technology to overcome the impedance matching problem of conventional feed networks. The 2x2 half bow tie array antenna is also truncated with spur lines for optimization of antenna performance. The array antenna unit can be realized in very simple and compact structure, as all the antenna elements and the feeding circuit is arranged on a Teflon glass fiber substrate without requiring any external network. The design frequency of the proposed antenna is 5 to 8 GHz (C-Band) and the obtained peak gain is 12.41 dBi. The resultant axial ratio indicates that linear polarization is achieved.This paper presents a novel method for QRS detection. To accomplish this task ECG signal was first filtered by using a third order Savitzky Golay filter. The filtered ECG signal was then preprocessed by a Wavelet based denoising in a real-time fashion to minimize the undefined noise level. R-peak was then detected from denoised signal after wavelet denoising. Windowing mechanism was also applied for finding any missing R-peaks. All the 48 records have been used to test the proposed method. During this testing, 99.97% sensitivity and 99.99% positive predictivity is obtained for QRS complex detection.

Formal verification of automated teller machine systems using SPIN

Formal verification is a technique for ensuring the correctness of systems. This work focuses on verifying a model of the Automated Teller Machine (ATM) system against some specifications. We construct the model as a state transition diagram that is suitable for verification. The specifications are expressed as Linear Temporal Logic (LTL) formulas. We use Simple Promela Interpreter (SPIN) model checker to check whether the model satisfies the formula. This model checker accepts models written in Process Meta Language (PROMELA), and its specifications are specified in LTL formulas.

Weather prediction using fuzzy rough clustering

Weather prediction is an important factor that can brought broad impact for other fields such as agriculture, business, and environmental. There were several researches conducted to develop tools or theories for weather prediction. In past few years, some researcher analyzed some seasonal attributes such as daily average temperature and daily average humidity to get better result in weather prediction. In this research, integration of classification and clustering technique is employed to analyze and predict the weather pattern. For the simulation, we used climate data in Perak, Surabaya, East Java, Indonesia which consist of temperature and humidity numerical data processed into categorical data using fuzzy rough clustering. In this research, we do four simulations: a month, a year, five years and the whole datasets. We transform humidity, temperature attributes into categorical data and speed of wind, still numerical data. Simulation results show that this method can predict the weather very well with t...

Mining fuzzy time interval sequential pattern on event log data using FP-Growth-Prefix-Span algorithms

Rapid technological developments caused the increasing number of computerized data processing. With the increasing complexity of business processes, business process management technologies such as ERP (Enterprise Resource Planning) are increasingly being used. This resulted in the availability of data more abundant so that excavation and search information from the dataset will be a valuable knowledge. In this paper, we have done the process mining to obtain an interesting pattern of event log data. In this research, data mining method that we are used is the sequential pattern mining algorithm using FP-Growth-Prefix Span. In addition, we are also used the fuzzy approach to handle the time interval of the analyzed data, so that the sequential pattern that produced become fuzzy time-interval sequential pattern. The application of these methods in a business processes that produce fuzzy time interval sequential pattern. From the analysis, the result shown that there is a minimum effect on the pattern of th...

Mining decision to discover the relation of rules among decision points in a non-free choice construct

Decision mining is a combination of process mining and machine learning algorithms to retrieve information on how data attributes in a business process affect routing of a case. It analyzes decision point by looking for XOR-splits in petri-net workflow model and examining rules for each choice based on available attributes using decision tree. The rules for each decision point are based on the attributes influence to the case. Meanwhile, a non-free choice construct is a mixture of choice and synchronization, which will create limited choices in the workflow. The limitation of choice will then affect the rules found in non-free choice construct using decision mining technique. Limitation of rules makes it possible to examine the relation among rules in the workflow. The relation of these rules will emerge a certain property of a non-free choice construct. Rules for two decision points within a non-free choice construct will have similarities. Regarding to this, when the same rule is found during a decision mining process, we can determine that the decision points have a non-free choice relationship.