Papers by Supriadi Rustad
A combination of machine learning model and density functional theory method to predict corrosion inhibition performance of new diazine derivative compounds
Materials Today Communications
Graded fuzzy edge detection for imperceptibility optimization of image steganography
The Imaging Science Journal
Impact Analysis of RGB Channels to the Quality of Imperceptibility in Image Steganography
2022 5th International Conference on Information and Communications Technology (ICOIACT)
DFT and microkinetic investigation of oxygen reduction reaction on corrosion inhibition mechanism of iron surface by Syzygium Aromaticum extract
Applied Surface Science
Sentiment Analysis Optimization Using Vader Lexicon on Machine Learning Approach
2022 International Seminar on Intelligent Technology and Its Applications (ISITIA)
Silhouette Analysis of Hand Gesture Dataset Using Histogram Profile Feature Extraction
2020 International Seminar on Application for Technology of Information and Communication (iSemantic)
Hand gesture dataset is a collection of hand gesture images. Several hand gesture datasets are fr... more Hand gesture dataset is a collection of hand gesture images. Several hand gesture datasets are freely available and can be used for various purposes, such as comparison or method testing. Processing the distribution of hand gesture image quality in the dataset has the opportunity to find potential models of hand gesture image quality for further research. This study tries to provide answers by exploring the quality of hand gesture images based on various datasets of public hand gestures. Then perform feature extraction based on the image histogram profile to get an overview of the range of color intensity values from the hand gesture image. The Herarchical Clustering method is used to build clusters based on histogram characteristics. The feasibility of the relationship between clusters was tested based on the silhouette index clustering method. The total number of hand gesture test images is 16 thousand data taken from 6 dataset sources that have been used in hand gesture recognition research. Based on the results of the processing, it is shown that the three clusters have no relationship feasibility or in other words the image clusters are independent.
Methyl butanoate is one of the compound which is obtained from triglyceride molecule. It has hydr... more Methyl butanoate is one of the compound which is obtained from triglyceride molecule. It has hydrocarbon components and hence may produce hydrocarbon through hydrodeoxygenation (HDO) or decarbonylation (DCO) processes. The first step to uncover the underlying mechanism of HDO or DCO is to find the active site of methyl butanoate adsorption over the catalyst. This study attempts to investigate the active site of methyl butanoate adsorption on MoS 2 surface. Stable bonding configuration for methyl butanoate adsorption on MoS 2 is investigated by using density functional theory (DFT). This investigation consists of geometry optimisation and adsorption energy calculations. The stable configuration of methyl butanoate adsorption on MoS 2 surface is found to be on top of Mo atom in Mo-edge surface.
Investigating the Impact of Synthetic Data Distribution on the Performance of Regression Models to Overcome Small Dataset Problems
2020 International Seminar on Application for Technology of Information and Communication (iSemantic), 2020
Machine learning is widely used in various fields, its ability to study data without having to de... more Machine learning is widely used in various fields, its ability to study data without having to determine the functional relationships that govern a system. However, small datasets often make it difficult for learning algorithms to make accurate predictions. To overcome this, an oversampling technique is needed. However, for the regression learning model this is not easy to do, because in regression to place synthesis data in a certain feature space must be accompanied by an appropriate target value, usually represented by an estimate function. Therefore in this paper oversampling is done by distributing synthetic data according to the Bus, Star, and Mesh topology, using the SMOTE (Synthetic Minority Over-sampling Technique) method. In the experiment, one of the ISE (Istanbul Stock Exchange) public datasets and one of the CF (Color Filter) real datasets were tested to measure the performance of the proposed oversampling technique. Besides, the results of experiments conducted on the same dataset using the MPV, FCM, and MMPV methods were used as a comparison. The results show that oversampling using the Bus, Star, or Mesh distribution results in better performance than without using oversampling. The ISE dataset tested using the proposed method has an average RMSE value smaller than the MPV, FCM, and MMPV methods. For CF datasets, the proposed method has an average RMSE value smaller than the MPV, FCM, and MMPV methods when the amount of training data is smaller than the amount of testing data.
Density functional study of methyl butanoate adsorption and its C–O bonds cleavage on MoS2-based catalyst with various loads of Ni promoters
Journal of Physics: Condensed Matter, 2019
Due to the increasing demands of new and renewable energy sources by utilising plant oils, uncove... more Due to the increasing demands of new and renewable energy sources by utilising plant oils, uncovering the underlying physico-chemical phenomena at the atomic level responsible for the effective deoxygenation plays a vital role in improving the performance of well-known as well as in looking for the possible new catalysts. This study aims at investigating the adsorption and C-O bonds cleavage of methyl butanoate (MB) over MoS2-based catalyst with various loads of Ni promoters by using first-principles density functional theory (DFT). This study employs surface model that never been used by previous researchers for their investigations of adsorption and bonds cleavage on Ni promoted MoS2-based catalysts. The introduction of nickel into MoS2-based catalyst allows the surface charges when interacts with MB to redistribute in such a way that induces stronger Coulombic attractive forces. This in turn could result in a more stable adsorption configuration. However only in certain Ni-loads will results in the most stable adsorption. Nevertheless the most stable adsorption of MB occurs on M-edge configuration which consists of two Ni atoms, i.e. M-2-Ni-A with adsorption energy at about -2.96 eV. As a comparison, the adsorption energy of MoS2 with the absent of Ni, i.e. M-0-Ni is just -2.79 eV. Since there are three C-O bonds in MB, this study proposes three possible reactions for these bonds to cleave. By using CI-NEB method, the activation energies of those three reaction are calculated. It shows that the presence of Ni with appropriate load could promote C-O bond cleavage, especially in one reaction C-O bond is weaken considerably. Further evaluation on bond dissociation energies of the closest C-C bond to the catalyst surface, M-2-Ni-A shows better reactivity on C-C bond cleavage than M-0-Ni, disregarding of those three reaction routes.
AIP Conference Proceedings, 2016
A solid waste composite was successfully made. Preliminary, the composite was synthesized using p... more A solid waste composite was successfully made. Preliminary, the composite was synthesized using polyurethane (PU) as binder mixed with the solid waste using simple mixing method and then hot-pressed at at pressure of 4 metric-tons and temperature of 80 C for 20 minutes. To enhance its strength, quartz sand partilces with varied content then were added into the PU-solid waste mixture. From the compressive strength test, it was obtained that PU/solid waste composite with PU fraction (w/w) of 0.43 has optimum compressive strength of 38.91 MPa. Having been added quartz sand having average particles size of 0.94 m, its compressive strength attains maximum at 40.47 MPa for quartz sand fraction (w/w) of 4.27 x 10-3. The strength is comparable to that of clay brick, slate stone, sandstone, limestone, alder wood, aspen wood, black cherry and pine woods. Therefore, this composite is very adequate to compete the building materials such as the bricks, stones and woods.
Academic ranks promotion in higher education in Indonesia during 1987–2014
2014 International Conference on Electrical Engineering and Computer Science (ICEECS), 2014
The system of academic rank structure and first appointment regulation for academic staff has bee... more The system of academic rank structure and first appointment regulation for academic staff has been established since 1987, this applied for either state and private-owned universities. The academic rank structure was divided into 9 level, starting from Associate Lecturer rate 100 credit points up to Full Professor rate 1000 credit points. Two years of staying in the previous position was mandatory before promotion to the higher rank, and accelerating or office caper was not possible. New regulation introduced in 1999 transformed the academic rank structure became simpler. By this new regulation Head Lecturer has been considered as associate professor level with rate 400, 550, and 700 credit points, while Professor rank rates 850 and 1050 credit points. It is eligible to get a rate promotion in the same academic ranks after 2 years in the current rate. However, The rate promotion is not possible if the adjacent rate belong to higher academic rank. A new statute passed by the parliament in 2006 stated that part time lecturer is no longer have academic ranks and also abolished Associate Lecturer rank rate 100 credit points. To have a promotion to be Professor from Head Lecturer rank, the candidate should publishes at least 1 article in accredited journal by Directorate General of Higher Education (DGHE) of Ministry of Education and Culture and fulfill the credit points needed. Special circumstances apply for office caper who jump directly from Associate Lecturer to Head Lecturer or from Lecturer to Professor, the candidate should has published at least 4 articles in acredited national journal, or equivalently 2 articles in international reputable journal. Since 2011 the DGHE has already implemented a new tighter assesment for academic rank promotion although still under the same regulation.
The mechanical properties of carbonized coconut char powder-based friction materials
Carbon, 2010
Carbonized coconut char powder-based friction materials for automotive brakes were produced using... more Carbonized coconut char powder-based friction materials for automotive brakes were produced using hot isostatic pressing machine at 190°C for 3h. The amounts of coconut char and magnesium oxide powders used in the mixing were optimized while fixing the compositions of other ingredients (styrene butadiene rubber, stearic acid, sulphur, zinc oxide, bakelite, calcium carbonate, brass, bronze and stainless steel), and effects
A first principle study of adsorption and dissociation of H2 molecule on MoS2 and Ni-promoted MoS2 surfaces
AIP Conference Proceedings
Digital image steganography survey and investigation (goal, assessment, method, development, and dataset)
Signal Processing
A Novel Approach on Linear Discriminant Analysis (LDA)
2020 International Seminar on Application for Technology of Information and Communication (iSemantic)
Linear Discriminant Analysis (LDA) is a method used for dimension reduction and classification. B... more Linear Discriminant Analysis (LDA) is a method used for dimension reduction and classification. By reducing the dimensions of data interpretation it becomes easier. A new LDA-based coordinate transformation (LDA-CT) approach has been developed that does not depend on the statistical nature of data distribution so that it is more robust to the influence of outliers. This approach transforms data from the old coordinates to the new coordinates so that an optimal gradient is obtained which maximizes the separation distance of the two groups in the projection space. Synthetic data are used to test the performance of this new LDA approach compared to existing LDA performance. The experimental results using synthetic data without and with outliers show that compared to the existing LDA, this new approach is able to make generalizations better and more robustly against the influence of outliers. For data that can be separated linearly, the LDA-CT Optimal method is able to separate classes as far as 0.705390519 better than existing LDA which only separates as far as 0.33440611. For data with outliers, LDA-CT Optimal accuracy is better than existing LDA with 91.67% compared to 75%.
Comparative Study of Classification Algorithms for Website Phishing Detection on Multiple Datasets
2022 International Seminar on Application for Technology of Information and Communication (iSemantic)
Indonesian Traffic Signs Recognition Using Convolutional Neural Network
2022 International Seminar on Application for Technology of Information and Communication (iSemantic)
Cybernetics and Information Technologies
The existence of a trade-off between embedding capacity and imperceptibility is a challenge to im... more The existence of a trade-off between embedding capacity and imperceptibility is a challenge to improve the quality of steganographic images. This research proposes to cross diagonal embedding Pixel Value Differencing (PVD) and Modulus Function (MF) techniques using edge area patterns to improve embedding capacity and imperceptibility simultaneously. At the same time still, maintain a good quality of security. By implementing them into 14 public datasets, the proposed techniques are proven to increase both capacity and imperceptibility. The cross diagonal embedding PVD is responsible for increasing the embedding capacity reaching an average value of 3.18 bits per pixel (bpp), and at the same time, the implementation of edge area block patterns-based embedding is a solution of improving imperceptibility toward an average value of PSNR above 40 dB and that of SSIM above 0.98. Aside from its success in increasing the embedding capacity and the imperceptibility, the proposed techniques r...
Inverted LSB image steganography using adaptive pattern to improve imperceptibility
Journal of King Saud University - Computer and Information Sciences, 2021
Abstract Various image steganography methods have been developed to improve the stego image quali... more Abstract Various image steganography methods have been developed to improve the stego image quality, i.e. imperceptibility, capacity, and security. This research proposes an adaptive method that can select the most optimal pattern to minimize the error ratio due to message embedding. This adaptive pattern can optimize the performance of the inverted LSB substitution method, based on the two-bit + least-significant-bit (LSB) pattern in the container image. Before embedding, the message and container image bits are tested and the error ratio is calculated using the inverted LSB substitution method for various possible patterns. The pattern that has the least error rate is selected to embed the message. The use of this adaptive pattern in inverted LSB image steganography significantly increases imperceptibility. Based on the test results and by comparing it to previous studies, it is found increased results, the PSNR value ranges from 52.49 to 57.45, and the SSIM ranges from 0.9991 to 0.9999 with 1 BPP capacity.
Jurnal Pendidikan Fisika Indonesia, 2016
The solid waste composite was successfully made. Preliminary, the composite was synthesized using... more The solid waste composite was successfully made. Preliminary, the composite was synthesized using polyurethane as binder mixed with the solid waste using simple mixing method and then hot-pressed at at pressure of 4 metric-tons and temperature of 100°C for 20 minutes. To enhance its strength, silica nanoparticles with varied content then were added in the polyurethane-solid waste mixture. From the compressive strength test, it was obtained that polyurethane-solid waste composite with solid waste volume fraction of 87.15% had optimum compressive strength of 160 MPa. Meanwhile, for silica addition with the fraction of 0.4975%, the compressive strength became 200 MPa, or increased 23% of that without nanosilica. The enhancement was also briefly confirmed from FTIR Spectroscopy where some polyurethane spectra shifted small due to silica addition, especially in amine and carbonyl groups as its active groups. The strength is better than of brick (80 MPa), shalestone (73 MPa), silstone (92...
Uploads
Papers by Supriadi Rustad