8 works
Publications
Papers, datasets and registered software. Abstracts and BibTeX expand in place.
Filter
-
Reference 1: , “CLC-YOLO: A Compact Channel-Gated Prototype Network for Real-Time Leakage-Aware Breast Ultrasound Lesion Segmentation,” 2nd International Conference on Artificial Intelligence and Technological Solutions (ICAITech 2026), IEEE, 2026.
Reliable breast ultrasound lesion segmentation requires accurate boundaries and evaluation that prevents patients or duplicate images from crossing data splits. We propose Channel Local Contrast (CLC), a compact refinement of the YOLO26 segmentation prototype head. CLC adds a fixed local high-pass residual controlled by 64 zero-initialized, bounded channel gates. Baseline and CLC were compared in five matched folds on each of four breast ultrasound datasets. BUS-BRA used patient-disjoint outer tests with separate inner validation. BUS-UCLM and BrEaST used patient-grouped validation folds; BUSI used duplicate-component groups because patient identifiers are unavailable. Group-macro Dice increased by 1.68, 3.11, 1.12, and 2.45 percentage points on BUS-BRA, BUS-UCLM, BUSI, and BrEaST, respectively. Only the BUS-BRA paired 95% confidence interval excluded zero. CLC adds 64 parameters and 0.0049 giga floating-point operations (GFLOPs). At 640 pixels, single-T4, batch-one, 16-bit floating-point (FP16) TensorRT graph times were 2.1478 ms for CLC and 2.0512 ms for baseline, excluding preprocessing and postprocessing. CLC increased group-macro Dice across all four datasets with a measured T4 forward-pass overhead of 0.0966 ms.
@misc{nizar2026clcyolo, author = {Nizar, M. Fazri and Rachmatullah, Muhammad Naufal and Supardi, Julian}, title = {{CLC-YOLO}: A Compact Channel-Gated Prototype Network for Real-Time Leakage-Aware Breast Ultrasound Lesion Segmentation}, year = {2026}, eprint = {2609.31702}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, doi = {10.48550/arXiv.2609.31702}, note = {Accepted to the 2nd International Conference on Artificial Intelligence and Technological Solutions (ICAITech 2026)} }ICAITech 2026 · 2026
Accepted
To appear · Palembang, Nov 2026
-
Reference 2: , “CoRef-DETR: Decoupled Global Context and Selective Boundary-Category Refinement for Underwater Instance Segmentation,” arXiv preprint arXiv:2606.08002, 2026.
Underwater instance segmentation supports marine surveys, aquaculture, and underwater robotics. Haze, colour casts, and low contrast blur object boundaries, and recent benchmarks distinguish up to 158 fine-grained categories. The strongest published methods mostly have 219 to 632 million parameters. This paper proposes CoRef-DETR, a compact detection transformer that targets three error sources of a real-time detector: context, boundaries, and categories. First, a decoupled global context (DGC) detector, with the base detector’s 33.4 M parameters, applies global self-attention to a 384-pixel token grid but supervises and decodes masks in a 576-pixel frame. Second, a posterior-conditioned boundary refiner with 47.7 k parameters corrects mask logits on predicted boundaries, and a quality score on the corrected masks re-ranks the detections. Third, a crop-probe category branch on frozen DINOv2 features revises the categories of at most three masks per image, where a rule fixed on validation data chooses soft fusion or a confident-disagreement gate. On five protocols of UIIS, UIIS10K, USIS10K, and USIS16K, CoRef-DETR achieves state-of-the-art mask average precision (AP), exceeding the strongest published results by 2.3 to 5.2 points, and outperforms three reproduced recent methods on the same test images (on USIS16K, with its category branch). In half precision with TensorRT, it processes an image in a median of 34 to 40 ms, JPEG decoding included, on a T4 GPU, 1.4 to 11 times faster than these methods. Ablations attribute most of DGC’s gain to the larger frame; an error analysis locates the remaining error in crowds of small objects.
@misc{nizar2026corefdetr, author = {Nizar, M. Fazri and Supardi, Julian and Rachmatullah, Muhammad Naufal}, title = {{CoRef-DETR}: Decoupled Global Context and Selective Boundary-Category Refinement for Underwater Instance Segmentation}, year = {2026}, eprint = {2606.08002}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, doi = {10.48550/arXiv.2606.08002} }arXiv 2606.08002 · 2026
Under review
Under review
-
Reference 3: , “Inter-Patient Split Fetal Head Ultrasound Segmentation Dataset in YOLO Polygon Format,” Harvard Dataverse, version 1 (CC0), 2026.
An inter-patient stratified train/val/test split (70/15/15) of 3,832 fetal head ultrasound images with YOLO-format polygon segmentation labels for three anatomical structures: Brain, Cavum Septi Pellucidi (CSP) and Lateral Ventricles (LV). The images come from the HC18 Grand Challenge (van den Heuvel et al., 2018) and the fetal head biometry annotation dataset of Alzubaidi et al. (2023). Every frame of a patient sits in exactly one partition, preventing the leakage that inflates scores when frames from one patient appear in both training and test sets; the split is seeded (seed = 42) for reproducibility.
@misc{nizar2026fetaldata, author = {Nizar, M. Fazri}, title = {{Inter-Patient Split Fetal Head Ultrasound Segmentation Dataset in YOLO Polygon Format}}, publisher = {Harvard Dataverse}, year = {2026}, version = {V1}, doi = {10.7910/DVN/FKXHLL}, url = {https://doi.org/10.7910/DVN/FKXHLL} }Harvard Dataverse · 2026
Dataset · CC0 · 3,832 images
-
Reference 4: , “Domain-Guided YOLO26 with Composite BCE-Dice-Lovász Loss for Multi-Class Fetal Head Ultrasound Segmentation,” arXiv preprint arXiv:2603.26755, 2026.
Segmenting fetal head structures from prenatal ultrasound remains a practical bottleneck in obstetric imaging. The current state-of-the-art baseline, proposed alongside the published dataset, adapts the Segment Anything Model with per-class Dice and Lovász losses but still depends on bounding-box prompts at test time. We build a prompt-free pipeline on top of YOLO26-Seg that jointly detects and segments three structures, Brain, Cavum Septi Pellucidi (CSP), and Lateral Ventricles (LV), in a single forward pass. Three modifications are central to our approach: (i) a composite BCE-Dice-Lovász segmentation loss with inverse-frequency class weighting, injected into the YOLO26 training loop via runtime monkey-patching; (ii) domain-guided copy-paste augmentation that transplants minority-class structures while respecting their anatomical location relative to the brain boundary; and (iii) inter-patient stratified splitting to prevent data leakage. On 575 held-out test images, the composite loss variant reaches a mean Dice coefficient of 0.9253, exceeding the baseline (0.9012) by 2.68 percentage points, despite reporting over three foreground classes only, whereas the baseline’s reported mean includes the easy background class. We further ablate each component and discuss annotation-quality and class-imbalance effects on CSP and LV performance.
@misc{nizar2026fetalhead, author = {Nizar, M. Fazri}, title = {Domain-Guided {YOLO26} with Composite {BCE}-Dice-Lov{\'a}sz Loss for Multi-Class Fetal Head Ultrasound Segmentation}, year = {2026}, eprint = {2603.26755}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, doi = {10.48550/arXiv.2603.26755} }arXiv 2603.26755 · 2026
Preprint
-
Reference 5: , “Indonesian Cross-Domain Benchmarks for Semantic Parsing and Text-to-SQL,” Harvard Dataverse, version 2 (CC0), 2026.
This dataset provides a standard benchmark for Indonesian Text-to-SQL research and cross-domain semantic parsing. Adapted from the well-established English Spider dataset, it addresses the underrepresentation of Indonesian in natural language interfaces for databases. The dataset pairs natural language questions in Bahasa Indonesia with complex SQL queries, developed through a rigorous four-stage pipeline of extraction, translation, cleaning, and conversion to ensure strict SQL syntax and database integrity.
@misc{nizar2026idspiderdata, author = {Nizar, M. Fazri and Abdiansah, Abdiansah}, title = {{Indonesian Cross-Domain Benchmarks for Semantic Parsing and Text-to-SQL}}, publisher = {Harvard Dataverse}, year = {2026}, version = {V2}, doi = {10.7910/DVN/C5AO0A}, url = {https://doi.org/10.7910/DVN/C5AO0A} }Harvard Dataverse · 2026
Dataset · CC0
-
Reference 6: , “IDSpider: Indonesian Standard Dataset for Text-to-SQL,” 2024 Ninth International Conference on Informatics and Computing (ICIC), IEEE, pp. 1–6, 2024.
This research presents IDSpider, a new standard dataset for Text-to-SQL research in Indonesian, developed by translating the well-established Spider dataset into Indonesian. Text-to-SQL is a critical technology that bridges the gap between natural language processing (NLP) and database management systems, allowing non-technical users to retrieve data from databases using simple, natural language queries. However, most existing datasets are in English, leaving non-English languages, especially Indonesian, underrepresented in the field. This paper describes the challenges encountered in translating both natural language questions and SQL queries, given the need for precision in maintaining SQL syntax and database structure integrity. We implemented a four-stage process consisting of Extraction, Translation, Cleaning, and Conversion to generate the IDSpider dataset. Furthermore, we tested the performance of the BRIDGE model on both the original Spider dataset and the translated IDSpider dataset. Results show that while the BRIDGE model performs well on Spider, its performance drops significantly when applied to IDSpider, primarily due to language differences and translation complexities. This research establishes the first benchmark for Indonesian Text-to-SQL tasks and lays the groundwork for further improvements in cross-lingual natural language interfaces for databases.
@inproceedings{abdiansah2024idspider, author = {Abdiansah, Abdiansah and Yusliani, Novi and Fathoni, Fathoni and Nizar, Muhammad Fazri and Salsabella, Aulia and Davi, Agi Agustian}, title = {{IDSpider}: Indonesian Standard Dataset for Text-to-{SQL}}, booktitle = {2024 Ninth International Conference on Informatics and Computing (ICIC)}, year = {2024}, month = oct, pages = {1--6}, address = {Medan, Indonesia}, publisher = {IEEE}, doi = {10.1109/ICIC64337.2024.10956918} }IEEE ICIC 2024 · 2024
Presented in Medan, Indonesia
-
Reference 7: , “Risk Meter Deterministic Algorithm for Website Security Assessment,” Indonesian copyright registration EC002025201921, Directorate General of Intellectual Property, 2025.
The Risk Meter algorithm classifies security risk levels from vulnerability-scan results that refer to CVE and CWE (open-source intelligence) reports. The scan covers general information (input, site, domain, IP, CMS, CDN and hosting), blacklist and whitelist status from nine verified database services, system details (errors, info and notices) and web-application findings.
@misc{nizar2025risk, title = {{Risk Meter Deterministic Algorithm for Website Security Assessment}}, author = {M. Fazri Nizar and Harisman Nizar and Nabil Pasha}, howpublished = {Indonesian copyright registration EC002025201921, Directorate General of Intellectual Property}, year = {2025}, month = {12} }DJKI copyright · 2025
Issued 4 December 2025 · EC002025201921
-
Reference 8: , “FazScan: Cross-Platform Software Application as Scanner of Information and Security of Websites,” Indonesian copyright registration EC00202509913, Directorate General of Intellectual Property, 2025.
FazScan is a cross-platform software application designed to analyse and improve website security by scanning website information and detecting security vulnerabilities. It uses scanning algorithms and open website-analysis APIs to report the website URL, IP, domain, CMS details, blacklist status and potential security risks.
@misc{nizar2025fazscan, title = {{FazScan: Cross-Platform Software Application as Scanner of Information and Security of Websites}}, author = {M. Fazri Nizar and Harisman Nizar}, howpublished = {Indonesian copyright registration EC00202509913, Directorate General of Intellectual Property}, year = {2025}, month = {1} }DJKI copyright · 2025
Issued 21 January 2025 · EC00202509913
No works match this filter.