Tanzilal Mustaqim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tanzilal Mustaqim has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Chastine Fatichah
Department of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
3 shared publications - Nanik Suciati
Institut Teknologi Sepuluh Nopember
3 shared publications - Ammar Sulthoni Adli
Institut Teknologi Bandung
1 shared publication - Amrul Faruq
University of Muhammadiyah Malang
1 shared publication - Aris Kusumawati
Institut Teknologi Telkom Surabaya
1 shared publication - Dedi Irawan
Universitas Riau
1 shared publication
Latest Publications
- Open Access
- 20 October 2026
- Published by Elsevier in SSRN Electronic Journal
A vertical ground reaction force-based gait deviation index using PCA and phase specific features
The Gait Deviation Index (GDI) provides a single measure of gait deviation by quantifying the distance from a normative gait pattern. However, conventional GDI requires three-dimensional motion-capture data, limiting its application when only kinetic measurements are available. This study investigates whether a compact vertical ground reaction force (vGRF)-based index can capture gait deviation comparable to that kinematic GDI. At a walking speed of 1.0 m/s, vGRF signals were normalized to body weight and gait-cycle time, segmented into four clinically interpretable phases, and represented using phase-specific kinetic and bilateral asymmetry features. Principal Component Analysis (PCA) was applied to the control group (P01-P30) to derive the normative feature space. The resulting distance-based vGRF deviation index (vGRF-DI) was scaled to a mean of 100 and standard deviation of 10 in the control population. A kinematic GDI was independently calculated from the same participants and used as the reference measure. The current processed dataset contained 41 participants, comprising 30 young healthy controls and 11 older healthy participants. The subject-level vGRF-DI showed a significant Pearson correlation with the kinematic GDI (r = 0.400, p = 0.0096), while the Spearman correlation was ρ = 0.270. Among the phase-specific measures, the strongest association was observed during p3 (push-off), with r = 0.448. The findings provide preliminary evidence that a compact vGRF-based feature representation can capture part of the gait-deviation variation represented by the kinematic GDI while providing phase-specific information. The vGRF-DI could therefore be considered a complementary measurement rather than an equivalent replacement for the kinematic GDI.
- 20 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA vertical ground reaction force-based gait deviation index using PCA and phase specific features
The Gait Deviation Index (GDI) provides a single measure of gait deviation by quantifying the distance from a normative gait pattern. However, conventional GDI requires three-dimensional motion-capture data, limiting its application when only kinetic measurements are available. This study investigates whether a compact vertical ground reaction force (vGRF)-based index can capture gait deviation comparable to that kinematic GDI. At a walking speed of 1.0 m/s, vGRF signals were normalized to body weight and gait-cycle time, segmented into four clinically interpretable phases, and represented using phase-specific kinetic and bilateral asymmetry features. Principal Component Analysis (PCA) was applied to the control group (P01-P30) to derive the normative feature space. The resulting distance-based vGRF deviation index (vGRF-DI) was scaled to a mean of 100 and standard deviation of 10 in the control population. A kinematic GDI was independently calculated from the same participants and used as the reference measure. The current processed dataset contained 41 participants, comprising 30 young healthy controls and 11 older healthy participants. The subject-level vGRF-DI showed a significant Pearson correlation with the kinematic GDI (r = 0.400, p = 0.0096), while the Spearman correlation was ρ = 0.270. Among the phase-specific measures, the strongest association was observed during p3 (push-off), with r = 0.448. The findings provide preliminary evidence that a compact vGRF-based feature representation can capture part of the gait-deviation variation represented by the kinematic GDI while providing phase-specific information. The vGRF-DI could therefore be considered a complementary measurement rather than an equivalent replacement for the kinematic GDI.
- Open Access
- 1 April 2025
- Published by Elsevier in Intelligent Systems with Applications
- Vol. 26
FocusAugMix: A data augmentation method for enhancing Acute Lymphoblastic Leukemia classification
- 1 April 2025
- Published by Elsevier in Intelligent Systems with Applications
- Vol. 26
Open AccessFocusAugMix: A data augmentation method for enhancing Acute Lymphoblastic Leukemia classification
- Open Access
- 15 August 2024
- Published by Perumnas Parit3 in JUMADI: Jurnal Masyarakat Mengabdi
- Vol. 1 (2) , 55-61
Socialization and Assistance in the Implementation of Social Assistance for the Dalegan Village Community, Gresik Regency
One of the government's efforts to improve the welfare of the Indonesian people, especially for people living below the poverty line, is the social assistance program. However, some people cannot utilize the social assistance program effectively due to a lack of understanding and access to information about the program. The purpose of community service activities is to increase public awareness and understanding of the various types of social assistance available so that community service activities can help the community in the process of applying for and receiving social assistance. It is expected that the social assistance program will be distributed on target through an approach and assistance involving village officials, community leaders, and direct assistance to village communities. Direct assistance to village communities can also be carried out to ensure that the social assistance distribution information system runs well. The results of community service activities can improve the welfare of village communities, reduce social disparities, increase the transparency of social assistance data, and improve the ability of village officials to manage social assistance. Community service activities can be a model for other villages in managing social assistance.
- 15 August 2024
- Published by Perumnas Parit3 in JUMADI: Jurnal Masyarakat Mengabdi
- Vol. 1 (2) , 55-61
Open AccessSocialization and Assistance in the Implementation of Social Assistance for the Dalegan Village Community, Gresik Regency
One of the government's efforts to improve the welfare of the Indonesian people, especially for people living below the poverty line, is the social assistance program. However, some people cannot utilize the social assistance program effectively due to a lack of understanding and access to information about the program. The purpose of community service activities is to increase public awareness and understanding of the various types of social assistance available so that community service activities can help the community in the process of applying for and receiving social assistance. It is expected that the social assistance program will be distributed on target through an approach and assistance involving village officials, community leaders, and direct assistance to village communities. Direct assistance to village communities can also be carried out to ensure that the social assistance distribution information system runs well. The results of community service activities can improve the welfare of village communities, reduce social disparities, increase the transparency of social assistance data, and improve the ability of village officials to manage social assistance. Community service activities can be a model for other villages in managing social assistance.
- Open Access
- 12 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 280-286
Identification of Acute Lymphoblastic Leukemia Subtypes on a Microscopic Image of Multicellular Blood Using Object Detection Model with Swin Transformer
Detecting subtypes of acute lymphoblastic leukemia (ALL) in multicellular microscopic images is crucial for early diagnosis and treatment. In the previous study, ALL subtype detection has often employed conventional methods requiring multiple phases, including WBC segmentation, touch cell separation, feature extraction, and classification. We compare object detection algorithms that require only a single learning framework and no additional steps. The performance of the YOLO, Mask R-CNN, and Mask R-CNN with Swin Transformer models for detecting ALL subtypes are compared. The aim of model comparison is to evaluate the performance in detecting the subtype of ALL with the best mAP value. In the detection of ALL subtypes, the Mask R-CNN with Swin Transformer surpasses all other models. The Mask R-CNN model with Swin Transformer produced the best global test results for the L1, L2 and L3 detection process, with mAP(0.5) and mAP(0.95) values of 94.5% and 68%, respectively.
- 12 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 280-286
Open AccessIdentification of Acute Lymphoblastic Leukemia Subtypes on a Microscopic Image of Multicellular Blood Using Object Detection Model with Swin Transformer
Detecting subtypes of acute lymphoblastic leukemia (ALL) in multicellular microscopic images is crucial for early diagnosis and treatment. In the previous study, ALL subtype detection has often employed conventional methods requiring multiple phases, including WBC segmentation, touch cell separation, feature extraction, and classification. We compare object detection algorithms that require only a single learning framework and no additional steps. The performance of the YOLO, Mask R-CNN, and Mask R-CNN with Swin Transformer models for detecting ALL subtypes are compared. The aim of model comparison is to evaluate the performance in detecting the subtype of ALL with the best mAP value. In the detection of ALL subtypes, the Mask R-CNN with Swin Transformer surpasses all other models. The Mask R-CNN model with Swin Transformer produced the best global test results for the L1, L2 and L3 detection process, with mAP(0.5) and mAP(0.95) values of 94.5% and 68%, respectively.
- Open Access
- 14 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 16108-16127
Deep Learning for the Detection of Acute Lymphoblastic Leukemia Subtypes on Microscopic Images: A Systematic Literature Review
Computer vision research in detecting and classifying the subtype Acute Lymphoblastic Leukemia (ALL) has contributed to computer-aided diagnosis with improved accuracy. Another contribution is to serve as an assistant and second opinion for doctors and hematologists in diagnosing the ALL subtype. Early detection can also rely on computer-aided diagnosis to determine initial treatment. The purpose of this study is to review the progress of research in the detection and classification of ALL subtypes. The method’s discussion focuses on the application of deep learning to the domain of object detection and classification. Motivations, challenges, and future research recommendations are thoroughly discussed to improve understanding and progress in this field of study. The study was carried out methodically by analyzing a collection of papers on the detection and classification of ALL subtypes published in science direct, IEEE, and PubMed from 2018 to 2022. The analysis of this paper field is included in the results of the selected paper. The paper selection from among 65 papers was based on inclusion and exclusion methods. Based on research methods and objectives, papers are divided into two large groups. The first group discusses the classification of ALL subtypes, while the second group discusses the detection of ALL subtypes. The discussion of prior research reveals some challenging issues and future work, such as the limited availability of the ALL subtypes dataset, the high computational complexity of the deep learning model, and further exploration of transformers in computer vision as a reference for research gaps that can contribute to future research.
- 14 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 16108-16127
Open AccessDeep Learning for the Detection of Acute Lymphoblastic Leukemia Subtypes on Microscopic Images: A Systematic Literature Review
Computer vision research in detecting and classifying the subtype Acute Lymphoblastic Leukemia (ALL) has contributed to computer-aided diagnosis with improved accuracy. Another contribution is to serve as an assistant and second opinion for doctors and hematologists in diagnosing the ALL subtype. Early detection can also rely on computer-aided diagnosis to determine initial treatment. The purpose of this study is to review the progress of research in the detection and classification of ALL subtypes. The method’s discussion focuses on the application of deep learning to the domain of object detection and classification. Motivations, challenges, and future research recommendations are thoroughly discussed to improve understanding and progress in this field of study. The study was carried out methodically by analyzing a collection of papers on the detection and classification of ALL subtypes published in science direct, IEEE, and PubMed from 2018 to 2022. The analysis of this paper field is included in the results of the selected paper. The paper selection from among 65 papers was based on inclusion and exclusion methods. Based on research methods and objectives, papers are divided into two large groups. The first group discusses the classification of ALL subtypes, while the second group discusses the detection of ALL subtypes. The discussion of prior research reveals some challenging issues and future work, such as the limited availability of the ALL subtypes dataset, the high computational complexity of the deep learning model, and further exploration of transformers in computer vision as a reference for research gaps that can contribute to future research.