Articles
Deteksi Fraud Menggunakan Metode Model Markov Tersembunyi Pada Proses Bisnis
Andrean Hutama Koosasi;
Riyanarto Sarno;
Abdul Munif
Jurnal Teknik ITS Vol 6, No 1 (2017)
Publisher : Direktorat Riset dan Pengabdian Masyarakat (DRPM), ITS
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (199.529 KB)
|
DOI: 10.12962/j23373539.v6i1.22328
Model Markov Tersembunyi merupakan sebuah metode statistik berdasarkan Model Markov sederhana yang memodelkan sistem serta membaginya dalam 2 (dua) state, state tersembunyi dan state observasi. Dalam pengerjaan tugas akhir ini, penulis mengusulkan penggunaan metode Model Markov Tersembunyi untuk menemukan fraud didalam sebuah pelaksanaan proses bisnis. Dengan penggunaan metode Model Markov Tersembunyi ini, maka pengamatan terhadap elemen penyusun sebuah kasus/kejadian, yakni beberapa aktivitas, akan diperoleh sebuah nilai peluang, yang sekaligus memberikan prediksi terhadap kasus/kejadian tersebut, sebuah fraud atau tidak. Hasil ekpserimen ini menunjukkan bahwa metode yang diusulkan mampu memberikan prediksi akhir dengan evaluasi TPR sebesar 87,5% dan TNR sebesar 99,4%.
Rancang Bangun Aplikasi MusicMoo dengan Metode MIR (Music Information Retrieval) pada Modul Fingerprint, Cover Song Recognition, dan Song Recommendation
Mochammad Faris Ponighzwa Rizkanda;
Riyanarto Sarno;
Dwi Sunaryo
Jurnal Teknik ITS Vol 6, No 2 (2017)
Publisher : Direktorat Riset dan Pengabdian Masyarakat (DRPM), ITS
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (450.796 KB)
|
DOI: 10.12962/j23373539.v6i2.23147
Industri musik sudah mulai merambah ke bidang komputer. Salah satunya adalah aplikasi SoundHound, Shazam, dan masih banyak lagi. Namun semua aplikasi tersebut hanya melakukan deteksi dari potongan suara yang direkam. Semua aplikasi tersebut bekerja dengan cara melakukan ekstrak fingerprint hanya dari beberapa segmen sinyal audio yang direkam. Pertama, penulis membangun database yang berisi fitur lagu. Di dalam fitur tersebut terdapat kumpulan nilai yang mengidentifikasikan suatu lagu. Dari deskripsi ini digunakan untuk melakukan pencarian pada suatu lagu. Kedua, melakukan proses pada fitur audio yang terkait. Ketiga, melakukan klasifikasi dan hasilnya adalah detail informasi fingerprint, cover song, dan rekomendasi pada suatu lagu.
Perbandingan Kemampuan Database NoSQL dan SQL dalam Kasus ERP Retail
Faizal Anugrah Bhaswara;
Riyanarto Sarno;
Dwo Sunaryono
Jurnal Teknik ITS Vol 6, No 2 (2017)
Publisher : Direktorat Riset dan Pengabdian Masyarakat (DRPM), ITS
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (520.823 KB)
|
DOI: 10.12962/j23373539.v6i2.24031
Makalah ini akan membahas dua jenis database, yaitu jenis Relational (SQL) dan Non-Relational (NOSQL). Mengingat dewasa ini para developer berlomba untuk memberikan database yang tepat dengan performa yang terbaik untuk aplikasinya. Kemudian makalah ini memberikan analisa perbandingan database NoSQL dengan SQL dalam hal kinerja, fleksibilitas, dan skalabilitas. Setelah terbukti database mana yang tepat, maka akan diterapkan aplikasi ERP Retail dengan yang berorientasikan multitenancy dengan tujuan agar aplikasi memiliki performa bagus, fleksibel dalam penyimpanan data, juga mendukung penyimpanan data yang terus berkembang seiring berjalannya waktu. Dalam uji coba yang telah dilakukan, database NoSQL terbukti memiliki kecepatan penyimpanan data yang lebih unggul dalam hal CRUD daripada SQL. Juga memiliki struktur penyimpanan data yang fleksibel karena model data berupa BSON (Binary JSON). Dan memiliki kemampuan untuk menjadi scalable dengan metode sharding. Jadi dalam hal ini database NoSQL akan lebih baik untuk diterapkan pada ERP Retail.
A survey of graph-based algorithms for discovering business processes
Riyanarto Sarno;
Kelly Rossa Sungkono
International Journal of Advances in Intelligent Informatics Vol 5, No 2 (2019): July 2019
Publisher : Universitas Ahmad Dahlan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26555/ijain.v5i2.296
Algorithms of process discovery help analysts to understand business processes and problems in a system by creating a process model based on a log of the system. There are existing algorithms of process discovery, namely graph-based. Of all algorithms, there are algorithms that process graph-database to depict a process model. Those algorithms claimed that those have less time complexity because of the graph-database ability to store relationships. This research analyses graph-based algorithms by measuring the time complexity and performance metrics and comparing them with a widely used algorithm, i.e. Alpha Miner and its expansion. Other than that, this research also gives outline explanations about graph-based algorithms and their focus issues. Based on the evaluations, the graph-based algorithm has high performance and less time complexity than Alpha Miner algorithm.
Reusability ontology in business processes with similarity matching
Meida Cahyo Untoro;
Riyanarto Sarno;
Nurul Fajrin Ariyani
Jurnal Informatika Vol 12, No 1: January 2018
Publisher : Universitas Ahmad Dahlan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26555/jifo.v12i1.a7175
The working technology will provide information and knowledge. Information and technology can be developed in various ways, by reusing the technologies. In this study modeled the ontology of SOPs using protégé. Ontology will be matched between ontology A and B to obtain similarity and reuse ontology to create a more optimal ontology. Matching is a matching process between both ontologies to get the same value from both ontologies. Jaro-Winkler distance is used to find commonality between ontology. The result of the Jaro-Winkler distance has a value of 0 and 1, in matching will be obtained value close to 0 or 1. On matching ontology obtained two tests using 40% SPARQL query. In the test it uses Jaro-Winkler distance with a value of 0.67. This research yields matching value between ontology A and ontology B which is the same so that reuse ontology can be done for better ontology
Aspect Based Sentiment Analysis: A Systematic Literature Review
Suhariyanto Suhariyanto;
Riyanarto Sarno;
Chastine Fatihah;
Edi Faisal
Journal of Applied Intelligent System Vol 5, No 1 (2020): Journal of Applied Intelligent System
Publisher : Universitas Dian Nuswantoro and IndoCEISS
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33633/jais.v5i1.3807
Aspect based sentiments can provide more detailed information about the sentiment (positive, negative, and neutral) based on an aspect in a review. It can provide better recommendations to users in decision making process. A number of previous studies have been conducted on aspect-based sentiment analysis indicating that survey is needed to provide an overview of the method available in aspect-based sentiment analysis. The survey method has been implemented since the last 5 years to obtain novelty from existing methods. The Systematic Literature Review (SLR) method is used to review a collection of 34 papers from various academic databases which focus on the aspect of extraction, sentiment analysis, and aspect aggregation. The papers will be sorted based on the focus of the method used. For each analysis, a detailed analysis is described on the contribution of the method to the aspect-based sentiment analysis alongside a comparison with other methods as well as advantages and disadvantages. The last section discusses the method commonly used in this study as well as future challenges in the study focusing on aspect-based sentiment analysis.
Business Process Improvement of Production Systems Using Coloured Petri Nets
Imam Mukhlash;
Widya Nilam Rumana;
Dieky Adzkiya;
Riyanarto Sarno
Bulletin of Electrical Engineering and Informatics Vol 7, No 1: March 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (430.09 KB)
|
DOI: 10.11591/eei.v7i1.845
The quality of information systems affects the company's business performance. Therefore, it is necessary to analyze business processes to determine any discrepancies between the planned business processes and the actual ones. Based on the results of this analysis, the business process can be improved. The fundamental factor of manufacturing companies is production process. In reality, there are many discrepancies between the actual business processes with the pre-planned, so that there should be analyzed. The analysis can be performed by modeling the business process using Coloured Petri Nets (CPN). In this study, the objectives are to determine the level of conformance checking of business processes, reachability graph and the bottleneck analysis. The results of the analysis are used to construct a recommended model. Based on the analysis of the case study, e.g. a steel industry in Indonesia, the recommended model has a better value than initial model.
A Combination of the Evolutionary Tree Miner and Simulated Annealing
Afina Lina Nurlaili;
Riyanarto Sarno
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 4: EECSI 2017
Publisher : IAES Indonesia Section
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (747.011 KB)
|
DOI: 10.11591/eecsi.v4.980
In recent years, process mining is important to discover process model from event logs; however the existing methods have not achieved good in overall fitness. In this context, this paper proposes a combination of the Evolutionary Tree Miner (ETM) and Simulated Annealing (SA). The ETM aims to reduce randomness of population so that it can improved the quality of individuals. SA aims to increase overall fitness in the population. The results of the proposed method which was compared to other approaches show that the proposes method had better in overall fitness and better quality of individuals.
Scalable Attack Analysis of Business Process based on Decision Mining Classification
Dewi Rahmawati;
Riyanarto Sarno
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 4: EECSI 2017
Publisher : IAES Indonesia Section
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (954.082 KB)
|
DOI: 10.11591/eecsi.v4.987
Banking crime is one of the widespread phenomena in 2016 are closely associated with the used of computer-based technology and internet networks that constantly evolving. One of them is the burglary of customer accounts through the internet banking facility. To overcome this, we need a method of how to detect a conspiracy of bank burglary case of customer accounts. The way to scalable is by get a mining decision to get a decision tree and from the decision tree to get a decision attribute value to determine the level of anomalies. Then of all the attributes decision point is calculated rate of fraud. The rate of fraud is classified through level of security of attack by the attacker then entropy gain is used to calculate the relative effort between the level of attacks in the decision tree. The results show that the method could classify three levels of attacks and the corresponding entropy gains. The paper uses decision trees algorithm, alpha++ and dotted chart analysis to analyze an attack that can be scalable. The results of the analysis show that the accuracy achieved by 0.87%.
Scalability Measurement of Business Process Model Using Business Processes Similarity and Complexity
Muhammad Ainul Yaqin;
Riyanarto Sarno;
Abd. Charis Fauzan
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 4: EECSI 2017
Publisher : IAES Indonesia Section
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (391.574 KB)
|
DOI: 10.11591/eecsi.v4.1033
The scalability of business process model shows the ability of a system to handle the amount of provided business process activity. In business process management, scalability is used to compare the size of a business process model to other business process models. This research focused on measuring the scalability of business process models. Every business processes were modeled using Petri Net. Petri Net was used as a business process model because of its simple model notation so it can be analyzed mathematically. The scalability of business processes had been done by comparing the similarity of some business processes and their scales. The similarity measurement method proposed were based on structural and behavioral using Jaccard coefficient, whereas the number of elements of the business process model and control flow complexity were used to measure its scale. Then, the scale value (0..1) and the similarity of the business process model was calculated by the specified formula. The result is a scalability value where the greater the value of the scalability, then the growth potential of the business process is also greater.