APAnggina Primanita

Anggina Primanita

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

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


Anggina Primanita has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A novel embedded approach to face recognition using multi-threaded controller based on weightless neural network

    by Ahmad Zarkasi, Hadipurnawan Satria, Anggina Primanita, Deris Stiawan

    This research presents a high efficiency embedded face recognition system based on the weightless neural network-face recognition algorithm (WNN-FRA) integrated with a multi-thread controller to enhance execution time and recognition accuracy under limited hardware resources. The system implements a center-scan feature alignment model to address resolution discrepancies between reference and input facial images. The multi-threaded architecture divides processing into three concurrent threads front, left, and right facial orientations each handling approximately 20 facial patterns. Experimental evaluation on a dataset of 60 facial images demonstrated a maximum recognition accuracy of 96.83% and an average execution time ranging from 16 to 34 milliseconds per dataset, confirming real-time performance. Comparative analysis shows that the multi-threaded approach reduced the execution time by over 67% compared to single-thread processing 0.09 second vs. 0.271 second, while maintaining balanced workload distribution across threads. Memory analysis revealed that the entire system required only 24 KB from the available 512 KB flash capacity, indicating efficient resource utilization. The results confirm that integrating WNN-FRA with multi-threading provides a robust, low-cost, and scalable solution for real-time facial pattern recognition in embedded environments.

  • Open Access

    Pemahaman Critical Thinking Dalam Menghadapi Olimpiade Sains Nasional (OSN) Untuk Guru SMA Al-Kautsar Bandar Lampung

    by Rizki Kurniati, Osvari Arsalan, Anggina Primanita, Muhammad Fachrurrozi, Hadipurnawan Satria, Muhammad Qurhanul Rizqie, Ermatita

    Berpikir kritis adalah kemampuan yang dibutuhkan oleh pengajar, terutama yang akan menghadapi Olimipade Sains Nasional (OSN). Tujuan dari kegiatan pengabdian kepada masyarakat ini adalah untuk meningkatkan kemampuan guru SMA dalam memahami permasalahan dengan berpikir kritis dalam menghadapi Olimpiade Sains Nasional (OSN). Melalui pelatihan dan pendampingan, para guru diberikan wawasan serta keterampilan praktis dalam mengintegrasikan metode berpikir kritis ke dalam pengajaran sehari-hari. Hasil kegiatan menunjukkan antusiasme tinggi dari peserta, yang terlihat dari interaksi aktif selama pelatihan. Kendala seperti keterbatasan infrastruktur jaringan diidentifikasi dan diusulkan solusi jangka panjangnya. Diharapkan dengan terselenggaranya kegiatan ini, kualitas pendidik dan pendidikan guru SMA mendapatkan dampak yang positif dan menjadi lebih baik. Hal ini dibuktikan dengan meningkatnya kemampuan guru SMA dalam memahmi soal berpikir kritis Kata Kunci : Berpikir Kritis; Gamifikasi; Olimpiade Sains Nasional; Pelatihan Guru; Pendidikan Digital

  • Open Access

    Adaptive Hint Generation for Educational Games Using Fuzzy Logic

    by Anggina Primanita, Hadipurnawan Satria, Muhammad Qurhanul Rizqie, Ananda Haykel Iskandar, Wibisena Nugraha

    The increasing interest in programming education has led to a wide variety of learner abilities. However, existing learning media often remain fragmented, necessitating the development of adaptive tools to cater to learners of varying skill levels. This study employs fuzzy logic to generate dynamic hints for players struggling to solve programming challenges in an educational game. The effectiveness of the system was evaluated through both simulation and real-world experiments. Simulation results indicate that the fuzzy logic system successfully generates personalized hints, with the highest frequency of hints provided to beginner players. Real-world testing using the GUESS-18 framework demonstrated high playability and excellent usability scores for the game.


  • Open Access

    American Sign Language Translation to Display the Text (Subtitles) using a Convolutional Neural Network

    by Muhammad Fajar Ramadhan, Samsuryadi Samsuryadi, Anggina Primanita

    Sign language is a harmonious combination of hand gestures, postures, and facial expressions. One of the most used and also the most researched Sign Language is American Sign Language (ASL) because it is easier to implement and also more common to apply on a daily basic. More and more research related to American Sign Language aims to make it easier for the speech impaired to communicate with other normal people. Now, American Sign Language research is starting to refer to the vision of computers so that everyone in the world can easily understand American Sign Language through machine learning. Technology continues to develop sign language translation, especially American Sign Language using the Convolutional Neural Network. This study uses the Densenet201 and DenseNet201 PyTorch architectures to translate American Sign Language, then display the translation into written form on a monitor screen. There are 4 comparisons of data splits, namely 90:10, 80:20, 70:30, and 60:30. The results showed the best results on DenseNet201 PyTorch in the train-test dataset comparison of 70:30 with an accuracy of 0.99732, precision of 0.99737, recall (sensitivity) of 0.99732, specificity of 0.99990, F1-score of 0.99731, and error of 0.00268. The results of the translation of American Sign Language into written form were successfully carried out by performance evaluation using ROUGE-1 and ROUGE-L resulting in a precision of 0.14286, Recall (sensitivity) 0.14286, and F1-score.


  • Open Access

    A new system for underwater vehicle balancing control based on weightless neural network and fuzzy logic methods

    by Ahmad Zarkasi, Hadipurnawan Satria, Anggina Primanita, Abdurahman Abdurahman, Nurul Afifah, Sutarno Sutarno

    The utilization of humans to be in the water for short time, resulting in limited area underwater that can be explored, so the information obtained is very limited, plus the influence of irregular water movements, changes in waves, and changes in water pressure, indirectly also constitutes obstacle to this problem. One of the best solutions is to develop underwater vessel that can travel either autonomously or by giving control of movement and navigation systems. New system for underwater vehicle balance control through weightless neural network (WNN) and fuzzy logic methods was proposed in this study. The aim was to simplify complicated data source on stability system using WNN algorithm and determine depth level of autonomous underwater vehicle (AUV) through fuzzy logic method. Moreover, speed control of underwater vehicle was determined using fuzzy rule-based design and inference. The tests were conducted by showing convergence performance of system in the form of AUV simulator. The results showed that proposed system could produce real-time motion balance performance, faster execution time, and good level of accuracy. This study was expected to produce real-time motion balance system with better performance, faster execution time, and good level of accuracy which could be subsequently used to design simple, cheap, and efficient hardware prototype.

  • Automatic Data Extraction Utilizing Structural Similarity From A Set of Portable Document Format (PDF) Files

    by Hadipurnawan Satria, Anggina Primanita

    Automatic Data Extraction Utilizing Structural Similarity From A Set of Portable Document Format (PDF) Files

  • Open Access

    Real-Time Occluded Face Identification Using Deep Learning

    by Muhammad Fachrurrozi, Anggina Primanita, Rafly Pakomgan, Abdiansah Abdiansah

    One of the most difficult aspects of face identification is face occlusion. Face occlusion is when anything is placed over the face, for example, a mask. Masks occlude multiple important facial features, like the chin, lips, nose, and facial edges. Face identification becomes challenging when important facial features are occluded. Using one of the deep learning algorithms, YOLOv5, this work tries to identify the face of someone whose face is occluded by a mask in real-time. A special program is being created to test the effectiveness of the YOLOv5 algorithm. 14 people's data were registered, and each person had 150 images used for training, validation, and testing. The images used are regular faces and mask-occluded faces. Nine distinct configurations of epoch and batch sizes were used to train the model. Then, during the testing phase, the best-performing configuration was chosen. Images and real-time input were used for testing. The highest possible accuracy of image identification is 100%, whereas the maximum accuracy of real-time identification is 64%. It was found during the testing that the brightness of the room has an influence on the performance of YOLOv5. Identifying individuals becomes more challenging when there are significant changes in brightness.


  • Open Access

    A Key Factor to Maintain Engagement: Case Study Using ‘Login System’

    by Gao Naying, Anggina Primanita, Mohd Nor Akmal Khalid, Hiroyuki Iida


  • Open Access

    Ear Image Recognition using Hyper Sausage Neuron

    by Samsuryadi Samsuryadi, Anggina Primanita

    It is important to distinguish an individual from a group of other individuals to ensure information security an d integrity. One of human body parts that has distinguishable characterics is the ear. Prior attempts on identification of hum an ear image has been implementing statistical pattern recogni tion which focusing more on classification between sample sets . This research attempts to build a robust ear image recognitio n system using Hyper Sausage Neuron (HSN) that concetrates on cognition process rather than classification. A recognition s oftware has been built and tested to recognize ear images. Ear images presented into the software has its geometrical moment invariants extracted. These moments is then used to build a se ven dimensional feature vector which will construct a network of HSN of each individual it represents. Different ear images f rom the same individual is presented into the software to test i ts accuracy. The experiment result shows that ear recognition using HSN has better accuracy and faster training time than p revious recognition attempts using statistical pattern recogniti on.

  • Open Access

    Ear Image Recognition using Hyper Sausage Neuron

    by Samsuryadi Samsuryadi, Anggina Primanita

    Ear Image Recognition using Hyper Sausage Neuron