- Universitas Katolik Indonesia Atma Jaya
Fakultas Teknik
Jalan Jenderal Sudirman 51
Jakarta 12930
Indonesia - +62 (021) 80827200
Lukas Lukas
Atma Jaya Catholic University of Indonesia, Engineering, Faculty Member
- main interests are Artificial Intelligence, Natural Language Processing, Psychology of Learning, Cognitive Engineeringedit
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Business, Psychology, Computer Science, Information Technology, Law, and 12 moreEducational Technology, Knowledge Management, Mathematics Education, Political Science, Politics, Technology Education, OPERATING SYSTEM, Cooperative Learning, Information and Communications Technology, World Wide Web, Teaching method, and Open Learning
Research Interests:
IT security is a significant concern of the internet because almost all communication occurs today. The purpose of testing personal data theft with the social engineering method is to ensure that the system and network on the user's... more
IT security is a significant concern of the internet because almost all communication occurs today. The purpose of testing personal data theft with the social engineering method is to ensure that the system and network on the user's Android have security holes to be hacked if the user is not aware of social engineering that allows data theft through the remote administration tool (RAT) which is accidentally downloaded on the Android User. Installing a RAT by applying social engineering is the possible and proper way to steal Android user privacy data. This study outlines some basic concepts of data theft, from recent call data and personal data to controlling Android users' cameras and microphones remotely.
This research compares different methods for optimizing and monitoring Kubernetes clusters. Three referenced journals are analyzed: "Kubernetes cluster optimization using hybrid shared-state scheduling framework" by Oana-Mihaela... more
This research compares different methods for optimizing and monitoring Kubernetes clusters. Three referenced journals are analyzed: "Kubernetes cluster optimization using hybrid shared-state scheduling framework" by Oana-Mihaela Ungureanu, Călin Vlădeanu, Robert Kooij; "Monitoring Kubernetes Clusters Using Prometheus and Grafana" by Salma Rachman Dira, Muhammad Arif Fadhly Ridha; and "Cluster Frameworks for Efficient Scheduling and Resource Allocation in Data Center Networks: A Survey" by Kun Wang, Qihua Zhou, Song Guo, and Jiangtao Luo. These journals explore various approaches to optimizing and monitoring Kubernetes clusters. This review concludes that selecting appropriate technologies for optimizing and monitoring Kubernetes clusters can enhance performance and resource management efficiency in data centre networks. The research addresses the problem of improving Kubernetes cluster performance through optimization and efficient monitoring. The requi...
Research Interests:
Research Interests:
ABSTRAKPupilometri merupakan metode pengukuran respons pupil terhadap stimulus. Kemampuan pupil mata dalam merespons cahaya diamati melalui pupillary light response (PLR). Penelitian mendapati PLR pasien demensia berbeda dengan pasien... more
ABSTRAKPupilometri merupakan metode pengukuran respons pupil terhadap stimulus. Kemampuan pupil mata dalam merespons cahaya diamati melalui pupillary light response (PLR). Penelitian mendapati PLR pasien demensia berbeda dengan pasien normal. Penelitian ini bertujuan merancang algoritma computer vision yang dapat mendeteksi pupil secara akurat, menampilkan respons pupil terhadap cahaya dalam bentuk grafik dan PLR pada sebuah aplikasi desktop, yang mengendalikan goggles berisi rangkaian kamera, pencahayaan, dan sensor jarak VL53L0X. Rekaman diproses dengan Local Binary Pattern (LBP) dan deteksi kontur untuk mendeteksi pupil. Data pengukuran diproses dan disimpan pada basis data lokal dan aplikasi web, sehingga tenaga medis dapat menentukan ada atau tidaknya gejala demensia pada pasien lansia. Tingkat ketelitian algoritma pengukuran pupil sebesar 73,33% yang didapatkan dari 30 kali pengujian.Kata kunci: computer vision, demensia, deteksi dini, pupillary light response, pupilometri ABS...
Research Interests:
One of the most common problems encountered during geothermal drilling operations is stuck pipe. The risk of stuck pipe is higher in geothermal drilling operations since geothermal drilling targets the lost circulation zone at reservoir... more
One of the most common problems encountered during geothermal drilling operations is stuck pipe. The risk of stuck pipe is higher in geothermal drilling operations since geothermal drilling targets the lost circulation zone at reservoir depth. The stuck pipe problem can cause a significant increase in drilling time and costs. The cost of a stuck pipe includes the time and money spent on extracting the pipe, fishing the parted BHA, and the effort required to plug and abandon the hole. Therefore preventing stuck pipes is far more cost effective than the most effective freeing procedures. Many researchers are working to identify the symptoms to reduce the risk of a stuck pipe. Due to the complexion of stuck pipe’s symptoms and indicators, some researcher proposed artificial intelligence (AI) as the tool to predict stuck pipes. Although researches have been made to build systems employing artificial intelligence (AI) to avoid stuck pipe occurrences in oil and gas drilling operations, fe...
Research Interests:
Research Interests:
Research Interests:
Pong's Snack is an MSMEs originating from Ponggang Village that produces various types of snacks such as opak, rengginang, cassava chips, wajid, potato chips, taro chips, banana chips, Seroja, kicimpring, and cistik. MSMEs in Ponggang... more
Pong's Snack is an MSMEs originating from Ponggang Village that produces various types of snacks such as opak, rengginang, cassava chips, wajid, potato chips, taro chips, banana chips, Seroja, kicimpring, and cistik. MSMEs in Ponggang Village still use conventional methods, such as marketing products by entrusting them to stalls, can order in advance via telephone number and the product is delivered directly to the customer. Therefore, the author helps MSMEs to be better known to the wider community by entering the products produced by MSMEs into the Pareang Sate Restaurant and selling their products online through the Tokopedia application. To be able to market products online, it is necessary to take steps that can be used as guidelines in digital marketing activities aimed at the target market and known as AIDA (Awareness, Interest, Desire, and Action). The first step taken by the author so that Pong's Snack MSMEs products can be known to consumers is to build awareness o...
Research Interests:
Research Interests:
Research Interests:
Peningkatan kebutuhan internet harus diseimbangkan dengan mempertahankan kinerja routing. Protokol routing Border Gateway Protocol (BGP) digunakan untuk menghubungkan semua Autonomous System (AS) di internet dengan mekanisme eksternal BGP... more
Peningkatan kebutuhan internet harus diseimbangkan dengan mempertahankan kinerja routing. Protokol routing Border Gateway Protocol (BGP) digunakan untuk menghubungkan semua Autonomous System (AS) di internet dengan mekanisme eksternal BGP (eBGP) untuk pertukaran informasi routing antar-AS. Namun, BGP masih bekerja dalam jaringan tradisional yang kompleks dengan pengendalian dan penerusan paket berada dalam device yang sama. Teknologi Software Defined Network (SDN) akan memisahkan control plane dan data plane, dengan pengendalian berpusat pada kontroler dan penerusan paket dijalankan oleh device jaringan. Penelitian ini mensimulasikan BGP pada teknologi SDN untuk melihat cara kerja BGP dalam pemilihan jalur jika ada link yang putus dan menguji kinerja dari protokol routing BGP dalam dua AS yang berbeda pada teknologi SDN. Simulasi dilakukan dengan menggunakan Mininet. Indikator kinerja yang diuji adalah jitter dan throughput. Dari serangkaian simulasi yang dilakukan, terlihat bahwa p...
Studies in economics domain tried to reveal the correlation between stock markets. Since the globalization era, interdependence between stock markets becomes more obvious. The Dynamic Interaction Network (DIN) algorithm, which was... more
Studies in economics domain tried to reveal the correlation between stock markets. Since the globalization era, interdependence between stock markets becomes more obvious. The Dynamic Interaction Network (DIN) algorithm, which was inspired by a Gene Regulatory Network (GRN) extraction method in the bioinformatics field, is applied to reveal important and complex dynamic relationship between stock markets. We use the data of the stock market indices from eight countries around the world in this study. Our results conclude that DIN is able to reveal and model patterns of dynamic interaction from the observed variables (i.e. stock market indices). Furthermore, it is also found that the extracted network models can be utilized to predict movement of the stock market indices with a considerably good accuracy.
Research Interests:
IDO (IOTA Oncology, Genetic networks), several PhD/postdoc & fellow grants; Flemish Government: Fund for Scientific Research FWO Flanders (several PhD/postdoc grants, projects
Research Interests:
The purpose of this research is to develop a fraud detection model on loan transactions at failed banks in the context of deposit and deposit guarantees mandated to the Indonesia Deposit Insurance Corporation (IDIC). The data used in this... more
The purpose of this research is to develop a fraud detection model on loan transactions at failed banks in the context of deposit and deposit guarantees mandated to the Indonesia Deposit Insurance Corporation (IDIC). The data used in this study is the data of a bank in the Jakarta area that had liquidated at the end of 2015. Meanwhile, data on loan transaction ranges ranged from 2010 to 2015. This research also focuses on improving the performance of detection models by using feature selection. With the feature selection, it expected that the impact of the reduced performance of the model exposed to high variance and high bias due to the many features used can handled better.
Research Interests:
Di tengah perkembangan teknologi, angka pengguna internet semakin meningkat setiap hari, namun keamanan dalam berselancar pada jaringan komputer/internet merupakan faktor yang sering kali dilupakan oleh penggunanya. Salah satu gangguan... more
Di tengah perkembangan teknologi, angka pengguna internet semakin meningkat setiap hari, namun keamanan dalam berselancar pada jaringan komputer/internet merupakan faktor yang sering kali dilupakan oleh penggunanya. Salah satu gangguan yang banyak terjadi pada jaringan komputer adalah penyebaran worms. Banyak upaya yang dapat dilakukan untuk menjaga keamanan dijaringan komputer tersebut contohnya adalah dengan melakukan pemeriksaan terhadap paket yang melintas pada jaringan tersebut, namun proses pengamatan tersebut akan menghasilkan suatu log data dalam jumlah yang sangat besar, yang akan memakan waktu untuk melakukan proses analisa. Penelitian ini bermaksud untuk mengembangkan suatu aplikasi untuk membantu mengolah log data hasil packet analyzer untuk menghasilan suatu laporan dengan cepat dan lebih akurat
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
The need of monitoring the water level of troughs is increasing. This is parallel with the growing of Wireless Sensor Network and Internet of Thing. By combining both approach, cattlemen can monitoring their troughs ubiquitous using their... more
The need of monitoring the water level of troughs is increasing. This is parallel with the growing of Wireless Sensor Network and Internet of Thing. By combining both approach, cattlemen can monitoring their troughs ubiquitous using their own personal device. This paper develop such system by using LoRa™ as the media between sensor hub and nodes, while Raspberry Pi is used as the gateway to push data into server. We have successfully tested the functionality of node to hub join mechanism, where a node should join to the closest hub, which marked by the highest RSSI of beacon signal. The designed system is able to wirelessly sense trough water level up to 50 simulated nodes.
Research Interests:
Research Interests: Computer Science, Time series Econometrics, Neural Network, Time Series Prediction, Time Series Data, and 10 moreMultiple Linear Regression, Exchange rate, STOCK EXCHANGE, Moving average, Stock Price, Chaotic Time Series, Polynomial Regression, Neural Information Processing, multi layer perceptron, and Statistical Method
Research Interests: Engineering, Mathematics, Radial Basis Function, Nuclear Magnetic Resonance, European Union, and 15 moreSupport Vector Machines, Magnetic Resonance Spectroscopy, Medicine, Discriminant Analysis, Humans, Data acquisition, Physical sciences, Magnetic Resonance, Magnetic, Brain Chemistry, Brain Neoplasms, Brain Tumour, Feature Reduction, Receiver Operating Characteristic (ROC) curve, and Linear discriminate analysis
Research supported by Research Council KULeuven: GOA-Mefisto 666, IDO (IOTA oncology, genetic networks), several PhD/postdoc & fellow grants; Flemish Govern-ment: FWO: PhD/postdoc grants, G.0407.02 (support vector machines), projects... more
Research supported by Research Council KULeuven: GOA-Mefisto 666, IDO (IOTA oncology, genetic networks), several PhD/postdoc & fellow grants; Flemish Govern-ment: FWO: PhD/postdoc grants, G.0407.02 (support vector machines), projects G.0115.01 ( ...
Research Interests:
Classification problems have arisen in many applications, attracting many researches to develop advanced classifier techniques. A method called Support Vector Machines (SVM) for pattern recognition and function estimation has been... more
Classification problems have arisen in many applications, attracting many researches to develop advanced classifier techniques. A method called Support Vector Machines (SVM) for pattern recognition and function estimation has been introduced by Vapnik (1995) in the ...
Research Interests:
Research Interests: Engineering, Mathematics, Analytical Chemistry, Magnetic Resonance Imaging, Magnetic Resonance Spectroscopy, and 15 moreMedicine, Discriminant Analysis, Humans, Linear Discriminant Analysis, Classification, Magnetic Resonance, High performance, Magnetic, Brain Chemistry, Mr Imaging, Performance Measure, Brain Neoplasms, Brain Tumour, Magnetic resonance image, and Linear discriminate analysis
Pada era Internet of Things (IoT), keamanan data merupakan salah satu faktor penting. Data dapat diamankan dengan menggunakan algoritma kriptografi. Algoritma kriptografi tersebut mengubah pesan asli menjadi suatu kode rahasia (enkripsi)... more
Pada era Internet of Things (IoT), keamanan data merupakan salah satu faktor penting. Data dapat diamankan dengan menggunakan algoritma kriptografi. Algoritma kriptografi tersebut mengubah pesan asli menjadi suatu kode rahasia (enkripsi) sedangkan proses sebaliknya disebut dekripsi. Data yang akan dienkripsi pada penelitian ini berupa boot log file yang terdapat pada Raspberry Pi dan Intel Compute Stick . Boot log file tersebut dienkripsi menggunakan algoritma Data Encryption Standard (DES) dan Data Encryption Standard Lightweight (DESL). Kedua algoritma tersebut memerlukan suatu kunci rahasia untuk melakukan enkripsi. Kunci rahasia yang digunakan untuk algoritma DES dan DESL lalu dienkripsi menggunakan algoritma Rivest-Shamir-Adleman (RSA) . Kemudian, data hasil enkripsi diunggah ke cloud dan dapat diunduh serta didekripsikan pada komputer client ( Virtual Machine ). Berdasarkan pengujian yang dilakukan pada penelitian ini, tidak diperoleh perbedaan waktu yang signifikan antara enk...
Research Interests:
The needs of monitoring the water level of troughs is increasing. This is parallel with the growing of Wireless Sensor Network and Internet of Thing. By combining both approach, cattlemen can monitoring their troughs ubiquitous using... more
The needs of monitoring the water level of troughs is increasing. This is parallel with the growing of Wireless Sensor
Network and Internet of Thing. By combining both approach,
cattlemen can monitoring their troughs ubiquitous using their
own personal device. This paper develop such system by using
LoRaTM as the media between sensor hub and nodes, while
Raspberry Pi is used as the gateway to push data into server. We have successfully tested the functionality of node to hub join mechanism, where a node should join to the closest hub, which marked by the highest RSSI of beacon signal. The designed system is able to wirelessly sense trough water level up to 50 simulated nodes.
Network and Internet of Thing. By combining both approach,
cattlemen can monitoring their troughs ubiquitous using their
own personal device. This paper develop such system by using
LoRaTM as the media between sensor hub and nodes, while
Raspberry Pi is used as the gateway to push data into server. We have successfully tested the functionality of node to hub join mechanism, where a node should join to the closest hub, which marked by the highest RSSI of beacon signal. The designed system is able to wirelessly sense trough water level up to 50 simulated nodes.
Research Interests:
Time-series prediction has been a very well researched topic in recent studies. Some popular approaches to this problem are the traditional statistical methods e.g. multiple linear regression and moving average, and neural network with... more
Time-series prediction has been a very well researched topic in
recent studies. Some popular approaches to this problem are the traditional statistical methods e.g. multiple linear regression and moving average, and neural network with the Multi Layer Perceptron which has shown its supremacy in time-series prediction. In this study, we used a different approach based on
evolving clustering algorithm with polynomial regressions to find repeating local patterns in a time-series data. To illustrate chaotic time-series data we have taken into account the use of stock price data from Indonesian stock exchange market and currency exchange rate data. In addition, we have also
conducted a benchmark test using the Mackey Glass data set. Results showed that the algorithm offers a considerably high accuracy in time-series prediction and could also reveal repeating patterns of movement from the past.
recent studies. Some popular approaches to this problem are the traditional statistical methods e.g. multiple linear regression and moving average, and neural network with the Multi Layer Perceptron which has shown its supremacy in time-series prediction. In this study, we used a different approach based on
evolving clustering algorithm with polynomial regressions to find repeating local patterns in a time-series data. To illustrate chaotic time-series data we have taken into account the use of stock price data from Indonesian stock exchange market and currency exchange rate data. In addition, we have also
conducted a benchmark test using the Mackey Glass data set. Results showed that the algorithm offers a considerably high accuracy in time-series prediction and could also reveal repeating patterns of movement from the past.
Research Interests:
Studies in economics domain tried to reveal the correlation between stock markets. Since the globalization era, interdependence between stock markets becomes more obvious. The Dynamic Interaction Network (DIN) algorithm, which was... more
Studies in economics domain tried to reveal the correlation between stock markets. Since the globalization era, interdependence between stock markets becomes more obvious. The Dynamic Interaction Network (DIN) algorithm, which was inspired by a Gene Regulatory Network (GRN) extraction method in the bioinformatics field, is applied to reveal important and complex dynamic relationship between stock markets. We use the data of the stock market indices from eight countries around the world in this study. Our results conclude that DIN is able to reveal and model patterns of dynamic interaction from the observed variables (i.e.
stock market indices). Furthermore, it is also found that the extracted network models can be utilized to predict movement of the stock market indices with a considerably good accuracy
stock market indices). Furthermore, it is also found that the extracted network models can be utilized to predict movement of the stock market indices with a considerably good accuracy
Research Interests:
Research Interests:
In least squares support vector machines (LS-SVM's) for function estimation Vapnik's -insensitive loss func-tion has been replaced by a cost function which corre-sponds to a form of ridge regression. In this way nonlin-ear... more
In least squares support vector machines (LS-SVM's) for function estimation Vapnik's -insensitive loss func-tion has been replaced by a cost function which corre-sponds to a form of ridge regression. In this way nonlin-ear function estimation is done by solving a linear ...
Research Interests:
There has been a growing research interest in brain tumor classification based on proton magnetic resonance spectroscopy (Math EqH MRS) signals. Four research centers within the EU funded INTERPRET project have acquired a significant... more
There has been a growing research interest in brain tumor classification based on proton magnetic resonance spectroscopy (Math EqH MRS) signals. Four research centers within the EU funded INTERPRET project have acquired a significant number of long echo Math EqH MRS signals for brain tumor classification. In this paper, we present an objective comparison of several classification techniques applied to the discrimination of four types of brain tumors: meningiomas, glioblastomas, astrocytomas grade II and metastases. Linear and non-linear classifiers are compared: linear discriminant analysis (LDA), support vector machines (SVM) and least squares SVM (LS-SVM) with a linear kernel as linear techniques and LS-SVM with a radial basis function (RBF) kernel as a non-linear technique. Kernel-based methods can perform well in processing high dimensional data. This motivates the inclusion of SVM and LS-SVM in this study. The analysis includes optimal input variable selection, (hyper-) parameter estimation, followed by performance evaluation. The classification performance is evaluated over 200 stratified random samplings of the dataset into training and test sets. Receiver operating characteristic (ROC) curve analysis measures the performance of binary classification, while for multiclass classification, we consider the accuracy as performance measure. Based on the complete magnitude spectra, automated binary classifiers are able to reach an area under the ROC curve (AUC) of more than 0.9 except for the hard case glioblastomas versus metastases. Although, based on the available long echo Math EqH MRS data, we did not find any statistically significant difference between the performances of LDA and the kernel-based methods, the latter have the strength that no dimensionality reduction is required to obtain such a high performance.