Papers by Mujiono Sadikin
Teknika
Amido Makmor Tulus Sejati merupakan perusahaan distributor multifunction printer merek Kyocera di... more Amido Makmor Tulus Sejati merupakan perusahaan distributor multifunction printer merek Kyocera di Indonesia. Evaluasi kinerja teknisi diperlukan untuk mempertahankan kepuasan customer terhadap penggunaan multifunction printer Kyocera. Proses penilaian kinerja teknisi masih dilakukan secara manual yang mengakibatkan hasil evaluasi kinerja teknisi yang diberikan kurang akurat atau kurang maksimal, sehingga perlu dilakukan suatu teknik pengolahan data secara cepat dan lebih akurat. Salah satunya dengan mempergunakan teknik data mining dengan menggunakan metode algoritma clustering. Metode algoritma clustering dipergunakan untuk mengelompokkan problem yang sering terjadi berdasarkan tipe mesin multifunction printer Kyocera. Pada penelitian ini diterapkan algoritma clustering K-Means dan K-Medoids, yang kemudian dilakukan uji clustering yang optimal dengan mempergunakan Metode Elbow dan Silhouette Score. Data yang dipergunakan dalam penelitian ini sebanyak 1.620 instan yang merupakan Dat...
Penentuan Respon Masyarakat Terhadap Kebijakan Pilkada pada masa Pandemi Covid-19 menggunakan Metode Algoritma Naïve Bayes-Classifier (NBC) dan Support Vector Machine (SVM)
Proceeding Seminar Nasional Ilmu Komputer, Jul 26, 2021
Many researches show that time series data is a kind of data which has biggest volume and growth ... more Many researches show that time series data is a kind of data which has biggest volume and growth compared to the others kind of data. Parallel with its huge volume and rapid growth, it is always needed new method, technique or approach to explore knowledge contained in time series data. One of many goals in data mining of time series is anomaly detection. By definition fractal is an object that has such self similarities in certain degree. This paper presents the results study of HFD (Higuchi Fractal Dimension) approach for clustering to detect the existence of an anomaly or deviation in time series data. This proposed method is applied to PT.PGN daily stock trade year 2004 to 2012 as test data. The results show that for value of discrete interval k = 5, 10, 15 their HFD tend to diverge and there are tend to converge to 2 for the greater value of k. Based on HFD time series clustering results, this approach can be used to divide the normal data and the other data that contain certai...
Format Jurnal Ilmiah Teknik Informatika, 2021
Perkembangan industri pangan di dunia termasuk Indonesia yang meningkat menyebabkan masyarakat te... more Perkembangan industri pangan di dunia termasuk Indonesia yang meningkat menyebabkan masyarakat terbiasa dengan segala sesuatu yang serba cepat dan praktis. Begitu pula dengan pola masyarakat dalam mengkonsumsi makanan yang sebisa mungkin dapat diselesaikan dalam waktu singkat. Hal tersebut berdampak pada timbulnya kebutuhan masyarakat terhadap makanan yang cepat dan instant. Kehadiran fast food langsung disukai masyarakat salah satunya produk yang dibuat dengan cara handmade, perusahaan ini menjual makanan frozen food dengan berbagai varian rasa dan memiliki pelanggan dari berbagai macam daerah. Makalah ini menyajikan hasil penelitian prediksi penjualan kebutuhan bahan baku dengan menggunakan perbandingan algoritma LSTM dan Arima untuk mengestimasi rasa yang paling laku di tahun yang akan datang. Hasil penelitian menunjukkan bahwa metode LSTM dengan komposisi data latih 63% dan data uji 37% , range interval [-1,1] dan epoch sebanyak 100 menghasilkan kinerja paling baik. Metode terse...
Spatial Clustering Algorithm Based on Neighboring Structure Approach
Clustering of spatial data is applied on information of object description (non-spatial attribute... more Clustering of spatial data is applied on information of object description (non-spatial attributes) and an object location (spatial attributes). Based on the first law of Geographic’s, the spatial attributes have patterns in their neighboring relationships. The patterns of neighboring relationship are found by clustering method that is proposed in present research. The clustering method is applied on non-spatial attributes which is represented as a non-numerical form and spatial attributes which is represented as sequence form simultaneously. The sequences represent the pattern of data linkages to its environments i.e. the specific data with its neighbors which are located in north, east, south and west direction (stated as a particle).The particle’s element is composed as sequences where each sequence consists of nine elements counted from the first element to ninth element. The particles are grouped based on the similarity of their constructor elements. Similarity of particles Pi,...
TELKOMNIKA (Telecommunication Computing Electronics and Control), 2018
In this digital era, it has been proven that the proper of e-learning system implementation provi... more In this digital era, it has been proven that the proper of e-learning system implementation provides various advantages and huge benefits. But to achieve the proper implementation is not an easy way since there are many obstacles have to be addressed. Beside the benefits and advantages, such as the other IT based system, e-learning also bring many risks that come from its environment or embedded in. Although many methods or approaches proposed to tackle those obstacles and risks, but the study that tackle those problems from IT Governance view is still limited. The study presents the report of the IT Governance approach to address some of the risks of eLearning system implementation such as: miss alignment with the enterprise goal and strategies, uncomplianceness with the government regulation, and unmatched with the stakeholder needs. The governance of eLearning system proposed has been implemented in the private university situated in Jakarta, Indonesia for two semesters. Based on the general observation, the University can get some benefits such as their succeed in maintaining its institution as the university that comply with government regulatory.
International Journal of Advanced Computer Science and Applications, 2021
Numerous studies have been carried out on computation and its applications to medical data with p... more Numerous studies have been carried out on computation and its applications to medical data with proven benefits for improving the quality of public health. However, not all research results or practical applications can be applied to all conditions but must be in accordance with the various contexts such as community culture, geographical, or citizen behaviors. Unfortunately, the use of digital data in Indonesia is still very limited. The study objective is to assess various data mining techniques to utilize data from laboratory test results collected from a private hospital in Indonesia in predicting the next patient treatment. Furthermore, various machine learning classification techniques were explored for the purpose. Based on the experiments, it was concluded that XGBoost with hyperparameter tuning produced the best accuracy level at 0.7579, compared to other classifiers. A better level of accuracy can be obtained by enriching the type of dataset used, such as the patient's...
Relation Extraction Based on Pattern Learning Approach
Semantically, objects in unstructured document are related each other to perform a certain entity... more Semantically, objects in unstructured document are related each other to perform a certain entity relation. This certain entity relation such: drug-drug interaction through their compounds, buyer-seller relationship through the goods or services, etc. Motivated by that kind of interaction, this study proposes a method to extract those objects and their interactions. It is presented a general framework of object-interaction mining of large corpora. The framework is started with the initial step in extracting a single object in the unstructured document. In this study, the initial step is a pattern learning method that is applied to drug-label documents to extract drug-names. We utilize an existing external knowledge to identify a certain regular expressions surrounding the targeted object and the probabilities of that regular expression, to perform the pattern learning process. The performance of this pattern learning approach is promising to apply in this relation extraction area. A...
Analisis Pola Keterkaitan Profil Dengan Tingkat Kehadiran Pegawai Menggunakan Clustering K-Means. Studi Kasus Pada Sekretariat BPJT
Berdasarkan amanat peraturan perundang undangan yang berlaku, Pemerintah wajib melaksanakan peneg... more Berdasarkan amanat peraturan perundang undangan yang berlaku, Pemerintah wajib melaksanakan penegakan disiplin terhadap para pegawai, baik Pegawai Negeri Sipil (PNS) atau Pegawai non PNS. Salah satu aspek yang terkait dengan tingkat disiplin pegawai adalah kehadiran. Kehadiran ini berkenaan dengan tanggung jawab pegawai saat bekerja. Pegawai yang hadir tepat waktu dan tidak terlambat saat masuk kerja bisa dikatakan mempunyai sifat disiplin baik. Penelitian ini dilakukan untuk mengetahui pola keterkaitan kehadiran dan karakteristik pegawai di lingkungan Sekretariat Badan Pengatur Jalan Tol (BPJT). Dataset yang digunakan dalam penelitian ini adalah rekap kehadiran pegawai tahun 2017. Analisis pola dilakukan menggunakan teknik clustering. Hipotesa yang diajukan dalam penilitian ini adalah bahwa ada hububungan antara masa kerja dengan tingkat kehadiran pegawai. Hasil analisis menunjukkan bahwa terdapat beberapa kelompok pegawai yang perlu ditingkatkan kedisiplinannya dan kelompok pegawa...
Musical and Semantic Structure in Poetry of Resistance a Case Study of Besisu and Al Fitory
Institute for Human Sciences and Cultural Studies, Dec 1, 2020
Building Natural Language Understanding System from User Manual to Execute Office Application Functions
2021 1st International Conference on Computer Science and Artificial Intelligence (ICCSAI)
The Graded CNN Technique to Identify Type of Food as The Preliminary Stages to Handle the Issues of Image Content Abundant
Proceedings of the 2020 12th International Conference on Computer and Automation Engineering, 2020
In this social media era, the marketing promotion is shifting from text to multimedia content. Th... more In this social media era, the marketing promotion is shifting from text to multimedia content. There is needed the new techniques and algorithm to deal with unrequested content posted to our social media page. The paper presents the study result of the application of Deep Learning method to identify the type of food i.e. junk-food or healthy food. In the experiment we explore some various layers of the Convolution Neural Network in classifying the type of food. We proposed another configuration stated as graded CNN. The results of the experiment show that our graded CNN technique proposed is outperform compared to the other trivial CNN configuration. Both of performance parameters, i.e. accuracy and time to process, confirm that our graded CNN technique is feasible to be considered as the powerful CNN variant in image classification domain. The average accuracy of the graded CNN is 9 % better than the common CNN, whereas the time to process is 400% more efficient.
Translation and Classification Algorithm of FDA-Drugs to DOEN2011 Class Therapy to Estimate Drug-Drug Interaction
Drug – drug interaction (DDI) is certain event in consuming of two or more drugs if one certain d... more Drug – drug interaction (DDI) is certain event in consuming of two or more drugs if one certain drug may influence the effects of another drug or otherwise. Drug – drug interactions may increase or decrease the effects of other drugs that affected, or could even harm the patient. The understanding of drug interactions is required both for the purposes of making a new drug or controlling its distribution. The research to understand drug interactions can be done in silo co for the efficiency. This paper presents the result study of drug – drug interaction estimation by performing the classification of the therapeutic class of FDA drug based on List of National Essential Drug 2011 (Daftar Obat Essensial Nasional /DOEN 2011) as a regulation of drug distribution released by Indonesia Government. The results study shows that from 2.384 unique FDA drugs, only 349 of them that are contained in 95 sub sub therapy classes of DOEN 2011.
Predictive genotype based on phenotype using the association rules mining
2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS), 2013
Genotype data is very important for many purposes since it contains such information of living or... more Genotype data is very important for many purposes since it contains such information of living organism. Unfortunately it is very hard to get the data. To get the data, it is needed a long and difficult chemical process. The purpose of this research is to develop a predictive gene sequence scheme in order to minimize the producing of the data. The scheme is made by finding the pattern of data correlation to perform a rule. The association rule mining method is used to build the rules andit can be used for genotype prediction. The prediction will be evaluated by the training and non training data on the experiment. The result of the experiment is an accuracy score of the predictive genotype. The accuracy of the training data is about 90% and the non training data is about 40%.
2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS), 2013
Kernel based integration data of gene expression and DNA copy number is used to analyze pattern o... more Kernel based integration data of gene expression and DNA copy number is used to analyze pattern of genes in breast cancer cell line. The integration data is clustered without any information about the number of k clusters. This paper proposes the use of intelligent kernel K-Means that is developed by combining intelligent K-Means and kernel K-Means. The technique is used to cluster data integration of gene expression and DNA copy number. The experiment results show that there are three clusters are successes to be found. Evaluation measure produce R value is 0.29.
Fractal dimension approach for clustering of DNA sequences based on internucleotide distance
2013 International Conference of Information and Communication Technology (ICoICT), 2013
ABSTRACT Recently, the volume of biological data increases exponentially. Problem of utilization ... more ABSTRACT Recently, the volume of biological data increases exponentially. Problem of utilization of this kind of data is not only concerning to the volume but also to its various format and storage distribution. To solve this kind of problems, some approaches require new methods, algorithms or tools to assist human being in getting beneficial from the biological data. This paper presents the usage of fractal dimension approach based on inter nucleotide distance to cluster DNA sequences. Inter nucleotide distance is a numerical representation of DNA sequences which is transformed to time series signal spectrum. Higuchi Fractal Dimension (HFD) is one of methods to estimate fractal dimension which it can be utilized to reduce time series dimension. HFD estimation then is applied to the signal spectrum and it is treated as input to clustering method. The result of this clustering shows that HFD approach can be considered as an alternative method for dimensional reduction purposes. Compared with previous study result as ground truth, the HFD approach clustering provides some similarities in certain degree. Tested with two kinds of data test sample, this approach results 6 and 7 group similarities of 10 groups.
Data forecasting to assist software verification & validation strategy preparation
2012 International Conference on Computer & Information Science (ICCIS), 2012
Software verification and validation is a critical phase in software development projects. But un... more Software verification and validation is a critical phase in software development projects. But unfortunately in many software development projects, software verification and validation rarely gets sufficient attention. Lack of attention is partly due to the assumption that the software verification & validation is not a priority and there for only limited resources can be allocated. This paper presents the result of study in using forecasting analysis model to assist software test strategy preparation. This study applies forecasting analysis to accumulation of individual transaction data that have been got before the system is tested. Those forecasting results are used as comparison tool to compare with the transaction data generated by system which is being tested. This study use subsidized fuel consumption monitoring system as a case study to apply the forecasting model. Test results on the case study, with some limitations, show that forecasting analysis and simulation model can be used as one of inputs to software verification & validation strategy preparation.
Sparse data for document clustering
2013 International Conference of Information and Communication Technology (ICoICT), 2013
ABSTRACT Document clustering which is a part of text mining framework is used to process models a... more ABSTRACT Document clustering which is a part of text mining framework is used to process models and real data collection of cancer documents into several groups. A vector space model of the documents based on their key phrases are formed and called sparse matrix which contains many zero values. A sparse dimensional reduction and several methods of clustering include K-means, Self Organizing and Non-negative Matrices Factorization (NMF) are applied to the data, then the results are compared. Sparse method in dimensional reduction step using Arnoldi Method provides a better result of clustering validity twice more than standard dimensional reduction result.
Journal of Advanced Management Science, 2014
As the IT operation in the other Enterprise, the implementation of IT in Higher Education has to ... more As the IT operation in the other Enterprise, the implementation of IT in Higher Education has to be directed and aligned with organizational strategy and program. The strategic alignment is one of five IT Governance focus areas. This paper presents the results, discussions and recommendations of IT Governance in Higher Education self assessment which is performed by COBIT 4.1 framework. The assessment is performed to IT Governance implementation in Mercu Buana University as a case study. The study result shows that the implementation of IT Governance in the university is still in the first stage of its development. Based on these results and some evidences collected, the study proposes some improvements such: it is needed to provide IT master plan, data and process custodian settlements must be performed, and the setup of such organizational structure which has capabilities enough to coordinate and deal with process / data owner and key user to drive University's IT Governance.
International Journal of Information and Education Technology, 2015
Uploads
Papers by Mujiono Sadikin