Ismail Marzuki

Ismail Marzuki

Auto-generated profile, based on publicly available information

Ismail Marzuki

Department of Chemical Engineering, Faculty of Engineering, Universitas Fajar, Makassar 90231, Indonesia

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2021 in Acta Polytechnica
Verified
Journal Article
Open access
PDF file
RURustam
Rustam
KUKoredianto Usman
Koredianto Usman
Mudyawati KamaruddinMudyawati Kamaruddin
Mudyawati Kamaruddin
DCDina Chamidah
Dina Chamidah
NONopendri
Nopendri
IMIsmail Marzuki
Ismail Marzuki
A possibilistic fuzzy c-means (PFCM) algorithm is a reliable algorithm proposed to deal with the weaknesses associated with handling noise sensitivity and coincidence clusters in fuzzy c-means (FCM) and possibilistic c-means (PCM). However, the PFCM algorithm is only applicable to complete data sets. Therefore, this research modified the PFCM for clustering incomplete data sets to OCSPFCM and NPSPFCM with the performance evaluated based on three aspects, 1) accuracy percentage, 2) the number of iterations, and 3) centroid errors. The results showed that the NPSPFCM outperforms the OCSPFCM with missing values ranging from 5% − 30% for all experimental data sets. Furthermore, both algorithms provide average accuracies between 97.75%−78.98% and 98.86%−92.49%, respectively.

15 February 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JLJongseok Lee
Jongseok Lee
WWWahyu Wiratama
Wahyu Wiratama
WLWoo Ju Lee
Woo Ju Lee
IMIsmail Marzuki
Ismail Marzuki
DSDonggyu Sim
Donggyu Sim
This study proposes a bilateral attention U-Net with a dissimilarity attention gate (DAG) for change detection on remote sensing imageries. The proposed network is designed with a bilateral dissimilarity encoding for the DAG calculation to handle reversible input images, resulting in high detection rates regardless of the order of the two input images for change detection. The DAG exploits all the combinations of joint features to avoid spectral information loss fed into an attention gate on the decoder side. The effectiveness of the proposed method was evaluated on the KOMPSAT-3 satellite images dataset and the aerial change detection dataset (CDD). Its performance was better than that of conventional methods (specifically, U-Net, ATTUNet, and Modified-UNet++) as it achieved average F1-score and kappa coefficient (KC) values of 0.68 and 66.93, respectively, for the KOMPSAT-3 dataset. For CDD, it achieved F1-score and KC values of 0.70 and 68.74, respectively, which are also better values than those achieved by conventional methods. In addition, we found that the proposed bilateral attention U-Net can provide the same changed map regardless of whether the image order is reversed.

21 June 2020 in Jurnal Akta Kimia Indonesia (Indonesia Chimica Acta)
Verified
Journal Article
Open access
PDF file
IMIsmail Marzuki
Ismail Marzuki
The use of sponge symbionts bacteria as marine biomaterials in the heavy metal bio-adsorption method is an effort to save the marine environment from contamination of heavy metal contaminants. The ocean is a giant container, most vulnerable to contamination of pollutants. The target of the research is to determine the potential, capacity and pattern of bio-adsorption of sponge symbionts bacteria against various pollutants so that the toxic properties of heavy metal contaminants can be minimize. The method used is to interact with the bacterial suspension on the test metal concentrations that have been determined. The parameters measured were optical density, pH and concentration of heavy metals after the interaction lasted several days and the calculation of capacity, efficiency and bio-adsorption patterns of bacterial isolates from sponges. Results: The pattern and bio-adsorption power of AC bacteria to Cr and Mn ions were higher than AC bacteria, the adaptability of AC and BS bacteria was stronger in Cr (III) contaminated media compared to Cr (VI) toxic media, causing bacterial cell population BS and AC in Cr (III) and Mn (II) media are more abundant than in Cr (VI) and Mn (VII) media, capacity and bio-adsorption efficiency of BS and AC bacteria agains Cr (III) ˃ Cr (VI) ions and Mn (II) ˃ Mn (VII), It is suspected that there is an influence of reactivity and toxic properties of the metal ion test on the performance of the sponge symbionts in bio-adsorption

7 September 2020 in IEEE Access
Verified
Journal Article
Open access
IMIsmail Marzuki
Ismail Marzuki
JLJongseok Lee
Jongseok Lee
DSDonggyu Sim
Donggyu Sim
This paper proposes an optimal rate control model based on deep neural network (DNN) features to improve the coding tree unit (CTU)-level rate control in high-efficiency video coding for conversational videos. The proposed algorithm extracts high-level features from the original and previously reconstructed CTU blocks based on a predefined DNN model of the visual geometry group (VGG-16) network. Then, the correlation of the high-level feature and quantization parameter (QP) values of previously coded CTUs is explored for subjective visual characteristics to estimate the CTU-level rate control model parameters (alpha and beta) and the bit allocation of each CTU. Therefore, this paper also proposes a new model for Lambda estimation for each CTU by improving its relationship with the estimated bits per pixel to control the rate and relative distortion. Furthermore, the Lambda and QP boundary settings were adjusted based on the proposed perceptual model to ensure the rate control accuracy of each CTU. The results of experiments with the proposed algorithm, when compared to the rate control model in HM-16.20, reveal higher bitrate accuracy and an average BD-rate gain based on PSNR, SSIM, and MSSSIM metrics using the low-delay-P configuration.

3 December 2021 in IEEE Access
Verified
Journal Article
Open access
IMIsmail Marzuki
Ismail Marzuki
JLJongseok Lee
Jongseok Lee
WWWahyu Wiratama
Wahyu Wiratama
DSDonggyu Sim
Donggyu Sim
This work proposes a rate control model based on deep convolutional features to improve the video coding performance of the HEVC encoders under the random access (RA) configuration. The proposed algorithm extracts high-level features from the original and previous coded frames using a pretrained visual geometry group (VGG-16) model by considering characteristics of a different temporal layer for the RA configuration. Subsequently, R– $\lambda $ parameters (alpha and beta), bit allocation, $\lambda $ estimation, and quantization parameter decision at frame-level are formulated by utilizing the extracted high-level features to maintain video quality and bitrate accuracy control. In addition, bit allocation at the group-of-picture (GOP)-level rate control is proposed with perceptual-based thresholding to control smooth bitrates and visual quality between adjacent GOPs. The results verify that the proposed algorithm is efficient in coding performance and bit accuracy by keeping visual quality. Compared with the existing R– $\lambda $ rate model in HM-16.20, the proposed models can achieve an average BD-rate gain of −4.39% and −8.74% in PSNR and MSSSIM metrics for the RA configuration, respectively.

9 October 2026 in Research in Ecology
Verified
Journal Article
Open access
PDF file
SYSattar Yunus
Sattar Yunus
IMIsmail Marzuki
Ismail Marzuki
MHMardiyyah Hasnawi
Mardiyyah Hasnawi
MFMuh. Ramzi Al Faqih
Muh. Ramzi Al Faqih
APAnnisa Sila Puspita
Annisa Sila Puspita
Open landfills generate complex mixtures of particulate and gaseous pollutants that can affect nearby communities. However, distance alone does not adequately explain their short-term spatial distribution. This study characterized multiple air pollutants surrounding the Tamangapa Landfill in Indonesia, compared concentrations between near and outer zones, and examined their relationships with distance and meteorological conditions. Field observations were conducted at nine locations situated 200–640 m from a central reference point. PM₁.₀, PM₂.₅, PM₁₀, formaldehyde, total volatile organic compounds (TVOC), CO, CO₂, CH₄, H₂S, O₂, and the lower explosive limit (LEL) were measured using complementary portable sensors. Analytical methods included descriptive statistics, Mann–Whitney tests, Cliff's delta, Spearman correlations, and Benjamini–Hochberg corrections. Particulate concentrations exhibited substantial spatial heterogeneity, with maximum PM₁.₀, PM₂.₅, and PM₁₀ concentrations of 146, 242, and 272 µg/m³, respectively. Mean concentrations in the near zone were approximately 3.6–3.7 times higher than those in the outer zone. TVOC showed a strong negative correlation with distance (rₛ = −0.812; p = 0.0079), although this association did not remain statistically significant after correction for multiple testing (q = 0.063). Pollutant distributions appeared to reflect interactions among distance, plume orientation, meteorological conditions, measurement time, and local activities. This study introduces a hybrid multi-sensor screening framework that integrates particulate, gaseous, spatial, and meteorological measurements for tropical landfill environments, particularly in resource-limited settings where conventional monitoring networks remain limited.