ZZZahir Zainuddin

Zahir Zainuddin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zahir Zainuddin has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Hybrid Robust Learning Framework for Multi-Scale Chicken Detection in Extreme Battery Cage Environments Using Augmented Transfer Learning

    by Abdul Malik I. Buna, Zahir Zainuddin, Syafruddin Syarif

    Multi-scale chicken detection in battery-cage farms is a challenging computer vision problem due to the severe occlusion from cage bars, low and inconsistent illumination, and high object density. This study proposes a hybrid robust learning framework based on augmented transfer learning to improve multi-scale chicken detection. The detector is built on Faster Region-based Convolutional Neural Networks (R-CNN) with a ResNet-50–FPN backbone. It is enhanced by an early-dilated convolutional block and a regularized custom head incorporating dropout and batch normalization. Transfer learning is applied through selective fine-tuning, in which only backbone stages 3–4 are retrained while earlier layers are frozen to preserve general representations. Four training schemes were evaluated: (a) baseline without augmentation, (b) online dynamic augmentation, (c) offline augmentation using Albumentations, and (d) hybrid offline+online augmentation. The augmentation pipeline includes rotation, horizontal flip, brightness/contrast adjustment, Gaussian blur, gamma correction, and resizing to 512×512, with COCO-format bounding boxes synchronized during transformation. Experiments using COCO evaluation show that the hybrid scheme achieves the best overall in-domain performance, reaching mAP@0.5 = 0.880, mAP@[0.50:0.95] = 0.414, and AR@100 = 0.483, corresponding to an absolute gain of 0.098 in mAP@0.5 over the offline-only scheme. Despite these gains, small-object detection remains unresolved, indicating the need for higher-resolution feature representations and anchor/grid redesign for micro-scale and heavily occluded instances. Overall, the findings indicate improved detection performance and in-domain generalization under naturally challenging battery-cage conditions. However, no dedicated corruption-based robustness benchmark or stress test was conducted; therefore, the results should not be interpreted as formal evidence of robustness to explicit illumination, blur, or noise perturbations.

  • Open Access

    Variable loaded brushless DC motor with six step commutation PID-based speed controller optimized by PSO algorithm

    by Fitriaty Pangerang, Faizal Arya Samman, Zahir Zainuddin, Rhiza S. Sadjad

    This research presents a method for regulating varying voltage as a DC source in a six-step commutation brushless DC (BLDC) motor drive through control proportional integral derivative (PID) as a simple strategy for controlling the speed of BLDC motors. Strengthening the control gain uses the particle swarm optimization (PSO) algorithm by minimizing the root mean square error (RMSE) and overshoot as fitness control characteristics. The performance of the motor with the proposed controller is analyzed and compared with an experimentally-simulated-tuned PID, hybrid gray wolf optimization–proportional integral (GWO-PI), and hybrid horse herd PSO-PID (HHH PSO-PID) under changing load and speed conditions. Simulation using compose-psim altair software. Control system response parameters such as RMSE, overshoot, electromagnetic torque ripple, and phase current ripple are measured and compared with the above controllers. The results show that the proposed controller is superior to a wide range of predefined system responses.


  • Open Access

    Balanced clustering for student admission school zoning by parameter tuning of constrained k-means

    by Zahir Zainuddin, Andi Alviadi Nur Risal

    The Indonesian government issued a regulation through the Ministry of Education and Culture, number 51 of 2018, which contains zoning rules to improve the quality of education in school educational institutions. This research aims to compare the performance of the k-means algorithm with the constrained k-means algorithm to model the zoning of each school area based on the shortest distance parameter between the school location and the domicile of prospective students. The study used data from 2248 prospective students and 22 public school locations. The results of testing the k-means algorithm in grouping showed the formation of non-circular patterns in the cluster membership with different numbers of centroid cluster members. In contrast, testing the constrained k-means algorithm showed balanced outcomes in cluster membership with a membership value of 103 for each school as the cluster center. The research findings state that the developed constrained k-means algorithm solves the problem of unbalanced data clustering and overlapping issues in the process of new student admissions. In other words, the constrained k-means algorithm can be a reference for the government in making decisions on new student admissions


  • Open Access

    Improving Community Digital Literacy Capability in Efforts to Build a Digital Village

    by Amil Ahmad Ilham, Zahir Zainuddin, Ingrid Nurtanio, Indra Bayu, Muhammad Nizwar, Adnan Adnan, Elly Warni, Zulkifli Tahir, Ais Prayogi Alimuddin, Christoforus Yohannes, et al.

    Digital desa merupakan program pemerintah yang berpusat pada pengembangan desa untuk meningkatkan kualitas hidup masyarakat desa melalui pemanfaatan teknologi dalam berbagai aspek pembangunan desa. Pengabdian masyarakat ini bertujuan untuk memberikan wawasan dan pengetahuan dasar untuk masyarakat terkait Desa Digital dan pengaplikasiannya untuk mendukung terwujudnya smart village. Kegiatan ini dilakukan di Desa Tamaona Kabupaten Bulukumba melalui proses sosialisasi yang dihadiri oleh 4 aparat desa dan 10 masyarakat produktif desa setempat. Informasi digital mengenai desa ini masih terbilang cukup minim di Internet, sementara potensi kekayaan alam dan produk yang ada di desa tersebut sangat baik. Oleh karena itu, kegiatan ini dilakukan untuk mendukung konsep digitalisasi desa serta sebagai ajang memperkenalkan potensi Desa Tamaona ke masyarakat luar. Pelaksanaan pengabdian ini dilakukan dengan sosialisasi aplikasi/system informasi desa menggunakan metode Participatory Rural Appraisal (PRA). Hasil pendataan awal menunjukkan bahwa masyarakat Desa Tamaona memiliki potensi yang cukup untuk pengembangan desa digital, yakni dilihat dari intensitas penggunaan internet oleh masyarakat yang sudah tinggi. Setelah dilakukan sosialisasi dan juga pelatihan penggunaan system informasi website, partisipan mengakui mendapatkan banyak kemudahan dari sisi pengaksesan informasi secara digital dibandingkan sebelum dilakukannya kegiatan ini. Tahap ini menjadi motivasi pengembangan lebih lanjut sumber daya teknologi untuk mencapai konsep desa cerdas yang juga dapat meningkatkan literasi digital bagi masyarakat desa Tamaona.


  • The Alumni’s Career Prediction Based on Academic Performances Utilizing Neural Network Algorithm

    by Ali Isra, Zahir Zainuddin, Zulkifli Tahir

    This current study implemented a neural network (ANN) algorithm for managing alumni’s career prediction data based on their academic performance. Tracer Study (TS) is a tracking for alumni regarding information related to the competence of higher education at the work environment. Such system was found beneficial for universities and higher education services as their reference to enchance the achievement of study program in order to produce alumni whose comptencies are needed by industries. The neural network algorithm is commonly used to classify data based on samples from training data. According to the results of the application of the neural network algorithm, it was found that the class precision accuracy was about 88.51% with a predicted waiting period of alumni to get a job (n) <= 6 months as many as 393 data, 6 months < n <= 1 year as 38 data and 1 year < n <= 2 years as 13 data


  • Open Access

    Augmented Reality 3D untuk Pengenalan Organ Tubuh Manusia

    by Andani Achmad, Zahir Zainuddin, Muhammad Fadhil Husain

    Marker Augmented Reality 3D pada Aplikasi Pengenalan Organ Tubuh Manusia adalah untuk membuat model belajar menggunakan teknologi Augmented Reality guna menyampaikan informasi tentang Pengenalan Organ Tubuh Manusia yang lebih interaktif dan inovatif dengan Teknologi Augmented Reality ke dalam satu aplikasi Android. Dalam mendukung penelitian ini digunakan Aplikasi Blender untuk pembuatan 3D Modelling dan aplikasi unity untuk pembuatan sistem yang di dukung dengan Bahasa Pemrograman C#, Vuforia SDK dalam implementasi Augmented Reality. Hasil pengujian deteksi 3D marker oleh kamera dapat di simpulkan bahwa tiap objek 3D memiliki jarak deteksi yang berbeda-beda. Hasil pengujian Virtual reality menunjukkan bahwa semua fungsi yang di ujikan dapat berjalan sesuai keinginan.


  • The Performance of Face Recognition Using the Combination of Viola-Jones, Local Binary Pattern Histogram and Euclidean Distance

    by Suherwin, Zahir Zainuddin, Amil Ahmad Ilham

    Achieving low recognition time and high accuracy in real-time face recognition is challenging. This study implements Viola-Jones, Local Binary Pattern Histogram, and Euclidean Distance for real-time face recognition and calculates the face detection time. The face image is detected using the Viola-Jones method; its features are extracted using the Local Binary Pattern Histogram, and the face is recognized using Euclidean Distance. This study processes sample images from 1013 students as training data, with 20 images represent each student. The experiments show that 268 of 342 testing data are recognized correctly, resulting in an accuracy of 78.4%, with average real-time recognition time of 0.93 seconds.


  • Open Access

    Prototype of Electrical Generator Device from Piezoelectric with Serial Configuration - Based on Mechanical Pressure

    by Yusran Yusran, A A Madia, Z Zainuddin

    This study discussed about of prototype of electrical generator device from piezoelectric with serial configuration - based on mechanical pressure. A prototype of a piezoelectric-based power plant that is able to convert mechanical energy (footing) or object load on piezoelectric into electrical energy was the aim of this research. The piezolectric generation system can be applied to serve limited loads and can be a support system for a distributed generation system. The method of research was device design and experimental testing. The experimental testing was carried out by varying pressures on piezoelectric to produce the desired output voltage. In testing, the pressure was generated by two different objects, a human footing and a object load with varying weight. The average voltage produced on human footing was 9.736 V for 60 kg body weight. The average voltage produced on object loads was 1.33 V for 5 kg object weight. This research has succeeded in making a prototype of a power plant using piezoelectric.