CNN-Based SIBI Sign Language Recognition Alphabet: Exploring the Impact of Hardware on Model Training
DOI:
https://doi.org/10.37385/jaets.v7i1.7071Keywords:
Sign Language Recognition, Alphabets, CNN, Hardware, ImpactAbstract
The recognition of Sign Language Alphabets (SLA) plays a vital role in human-computer interaction, especially for individuals with auditory disabilities. This study aims to evaluate the impact of different hardware configurations—specifically CPU, GPU, and memory setups—on the training efficiency and recognition performance of a Convolutional Neural Network (CNN)-based model for SLA using the SIBI dataset. The novelty of this research lies in its focus on hardware-aware deep learning optimization for Indonesian sign language (SIBI), an underexplored area. The model was trained on 3,468 labeled hand gesture images representing 24 SIBI alphabet signs. Experiments were conducted on CPU (Intel Xeon 2.00 GHz) and GPU (Nvidia Tesla T4) platforms using a consistent CNN architecture. The training time was significantly reduced by 45.5%, from 1 hour 39 minutes to just 54 minutes, while the accuracy remained consistent at 96.7%, showing no significant change between the two setups. These results demonstrate the significance of parallel processing and memory bandwidth in enhancing model convergence and generalization. The findings are relevant for real-time SLA deployment with hardware constraints on embedded or mobile platforms. Overall, the study underscores the importance of hardware optimization in accelerating CNN training and improving performance in sign language recognition systems.
Downloads
References
Abdalla, A., Alsereidi, A., Alyammahi, N., Qehaizel, F. B., Ignatious, H. A., & El-Sayed, H. (2023). An innovative Arabic text sign language translator. Procedia Computer Science, 224, 425–430. https://doi.org/10.1016/j.procs.2023.09.059
Abdallah, M. S., Hemayed, E., Abdalla, M. S., & Hemayed, E. E. (2013). Dynamic hand gesture recognition of Arabic sign language using hand motion trajectory features. https://www.researchgate.net/publication/258172682
Abdallah, M. S., Samaan, G. H., Wadie, A. R., Makhmudov, F., & Cho, Y. I. (2023). Light-weight deep learning techniques with advanced processing for real-time hand gesture recognition. Sensors, 23(1). https://doi.org/10.3390/s23010002
Abdullah, B. A. Al, Amoudi, G. A., & Alghamdi, H. S. (2024). Advancements in sign language recognition: A comprehensive review and future prospects. IEEE Access, 12, 128871–128895. https://doi.org/10.1109/ACCESS.2024.3457692
Al Moustafa, A. M. J., Shafry, M., Rahim, M., Khattab, M. M., Zeki, A. M., Matter, S. S., Soliman, A. M., & Ahmed, A. M. (2024). Arabic sign language recognition systems: A systematic review. Indian Journal of Computer Science and Engineering, 15. https://doi.org/10.21817/indjcse/2024/v15i1/241501008
Alsharif, B., Altaher, A. S., Altaher, A., Ilyas, M., & Alalwany, E. (2023a). Deep learning technology to recognize American sign language alphabet. Sensors, 23(18). https://doi.org/10.3390/s23187970
Alsharif, B., Altaher, A. S., Altaher, A., Ilyas, M., & Alalwany, E. (2023b). Deep learning technology to recognize American sign language alphabet. Sensors, 23(18). https://doi.org/10.3390/s23187970
Arya, N., Soni, T., Pattanaik, M., & Sharma, G. K. (2022). Energy-efficient logarithmic-based approximate divider for ASIC and FPGA-based implementations. Microprocessors and Microsystems, 90, 104498. https://doi.org/10.1016/j.micpro.2022.104498
Ben Atitallah, B., Hu, Z., Bouchaala, D., Hussain, M. A., Ismail, A., Derbel, N., & Kanoun, O. (2022). Hand sign recognition system based on EIT imaging and robust CNN classification. IEEE Sensors Journal, 22(2), 1729–1737. https://doi.org/10.1109/JSEN.2021.3130982
Bryzgalov, P., & Maeda, T. (2024). Using benchmarking and regression models for predicting CNN training time on a GPU. Proceedings of the 4th Workshop on Performance Engineering, 8–15. https://doi.org/10.1145/3660317.3660323
Choi, J., Lee, H. J., Sohn, K., Yu, H. S., & Rhee, C. E. (2024). Accelerating CNN training with concurrent execution of GPU and processing-in-memory. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3488004
Darmawan, I. D. M. B. A., Linawati, L., Sukadarmika, G., Wirastuti, N. M. A. E. D., Pulungan, R., Mulyanto, & Hariyanti, N. K. D. (2023). Advancing total communication in SIBI: A proposed conceptual framework for sign language translation. ICSGTEIS 2023, 23–28. https://doi.org/10.1109/ICSGTEIS60500.2023.10424020
Duarte, A., Palaskar, S., Ventura, L., Ghadiyaram, D., Dehaan, K., Metze, F., Torres, J., & Giro-I-Nieto, X. (2021). How2Sign: A large-scale multimodal dataset for continuous American sign language. http://how2sign.github.io/
Fadlilah, U., Mahamad, A. K., & Handaga, B. (2021a). The development of Android for Indonesian sign language using Tensorflow Lite and CNN: An initial study. Journal of Physics: Conference Series, 1858(1). https://doi.org/10.1088/1742-6596/1858/1/012085
Fadlilah, U., Mahamad, A. K., & Handaga, B. (2021b). The development of Android for Indonesian sign language using Tensorflow Lite and CNN: An initial study. Journal of Physics: Conference Series, 1858(1). https://doi.org/10.1088/1742-6596/1858/1/012085
Fadlilah, U., Prasetyo, R. A. R., Mahamad, A. K., Handaga, B., Saon, S., & Sudarmilah, E. (2022). Modelling of basic Indonesian sign language translator based on Raspberry Pi technology. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 22(3), 574–584. https://doi.org/10.17586/2226-1494-2022-22-3-574-584
Fadlilah, U., Wismoyohadi, D., Mahamad, A. K., & Handaga, B. (2019). BISINDO information system as potential daily sign language learning. AIP Conference Proceedings, 2114. https://doi.org/10.1063/1.5112492
Ferraz, O., Subramaniyan, S., Chinthala, R., Andrade, J., Cavallaro, J. R., Nandy, S. K., Silva, V., Zhang, X., Purnaprajna, M., & Falcao, G. (2022). A survey on high-throughput non-binary LDPC decoders. IEEE Communications Surveys & Tutorials, 24(1), 524–556. https://doi.org/10.1109/COMST.2021.3126127
Handayani, A. N., Akbar, M. I., Ar-Rosyid, H., Ilham, M., Asmara, R. A., & Fukuda, O. (2022). Design of SIBI sign language recognition using artificial neural network backpropagation. ICICyTA 2022, 192–197. https://doi.org/10.1109/ICICyTA57421.2022.10038205
Hashi, A. O., Hashim, S. Z. M., & Asamah, A. B. (2024). A systematic review of hand gesture recognition: An update from 2018 to 2024. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3421992
Hekmat, A., Ali, M., Abbas, H. H., & Shahadi, I. (2022). Sign language recognition and hand gestures review. https://kjes.uokerbala.edu.iq/
Hu, Y., Liu, Y., & Liu, Z. (2022). A survey on convolutional neural network accelerators: GPU, FPGA and ASIC. ICCRD 2022, 100–107. https://doi.org/10.1109/ICCRD54409.2022.9730377
Huang, H., Li, Y., & Zhou, X. (2023). Accelerating point clouds classification in dynamic graph CNN with GPU Tensor Core. ICPADS, 1725–1732. https://doi.org/10.1109/ICPADS60453.2023.00240
Hussin, S. K., Mohamed, O., Mustafa, Ahmed, E., & Mahmoud, O. (2021). Real-time Arabic sign language translator using MediaPipe and LSTM. PLOMS Journal of Artificial Intelligence, 1–13. https://plomscience.com/journals/index.php/PLOMSAI/index
Irvanizam, I., Horatius, I., & Sofyan, H. (2023). Applying artificial neural network based on backpropagation method for Indonesian sign language recognition. International Journal of Computing and Digital Systems, 14(1), 975–985. https://doi.org/10.12785/ijcds/140176
Kwenda, C., Gwetu, M., & Fonou-Dombeu, J. V. (2023). Ontology with deep learning for forest image classification. Applied Sciences, 13(8). https://doi.org/10.3390/app13085060
Latif, G., Mohammad, N., Alghazo, J., & AlKhalaf, R. (2019). ArASL: Arabic alphabets sign language dataset. Data in Brief, 23. https://doi.org/10.1016/j.dib.2019.103777
Li, H., Wang, Z., Yue, X., Wang, W., Tomiyama, H., & Meng, L. (2023). An architecture-level analysis on deep learning models for low-impact computations. Artificial Intelligence Review, 56(3), 1971–2010. https://doi.org/10.1007/s10462-022-10221-5
Li, L., Li, Y., & Tan, H. (2024). DeepDecompose: A distributed inference framework for CNN on GPU-equipped edge clusters. ICCNIT 2024, 540–544. https://doi.org/10.1145/3670105.3670200
Lu, C., Kozakai, M., & Jing, L. (2023). Sign language recognition with multimodal sensors and deep learning methods. Electronics, 12(23). https://doi.org/10.3390/electronics12234827
Luong, S. (2023). Video sign language recognition using pose extraction and deep learning models [Thesis]. https://doi.org/10.31979/etd.jm4c-myd4
Mohammadi, M., Chandarana, P., Seekings, J., Hendrix, S., & Zand, R. (2022). Static hand gesture recognition for American Sign Language using neuromorphic hardware. Neuromorphic Computing and Engineering, 2(4). https://doi.org/10.1088/2634-4386/ac94f3
Mohammadi, M., Smith, H., Khan, L., & Zand, R. (2023). Facial expression recognition at the edge: CPU vs GPU vs VPU vs TPU. GLSVLSI 2023, 243–248. https://doi.org/10.1145/3583781.3590245
Muis, A., Sunardi, S., & Yudhana, A. (2024). CNN-based approach for enhancing brain tumor image classification accuracy. International Journal of Engineering, 37(5), 984–996. https://doi.org/10.5829/ije.2024.37.05b.15
Nadir, M. N., Siraj Rathore, M., Hayat, A., & Mansoor, J. A. (2024). CPU vs GPU: Performance comparison of OpenCL applications on a heterogeneous architecture. Journal of Computing & Biomedical Informatics, 7(2). https://doi.org/10.56979/702/2024
Nguyen, P. T., Nguyen, T. H., Hoang, N. X. N., Phan, H. T. B., Vu, H. S. H., & Huynh, H. N. (2023). Exploring MediaPipe optimization strategies for real-time sign language recognition. CTU Journal of Innovation and Sustainable Development, 15(ISDS), 142–152. https://doi.org/10.22144/ctujoisd.2023.045
Olisah, C. C., Smith, L., & Smith, M. (2022). Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective. Computer Methods and Programs in Biomedicine, 220, 106773. https://doi.org/10.1016/j.cmpb.2022.106773
Pacini, F., Pacini, T., Lai, G., Zocco, A. M., & Fanucci, L. (2024). Design and evaluation of CPU-, GPU-, and FPGA-based deployment of a CNN for motor imagery classification. Electronics, 13(9). https://doi.org/10.3390/electronics13091646
Ping, Y., Jiang, H., Liu, X., Zhao, Z., Zhou, Z., & Chen, X. (2024). Latency-based inter-operator scheduling for CNN inference acceleration on GPU. IEEE Transactions on Services Computing, 17(1), 277–290. https://doi.org/10.1109/TSC.2023.3345952
Pitonak, R., Mucha, J., Dobis, L., Javorka, M., & Marusin, M. (2022). CloudSatNet-1: FPGA-based hardware-accelerated quantized CNN for satellite on-board cloud coverage classification. Remote Sensing, 14(13). https://doi.org/10.3390/rs14133180
Rajput, S. H., Mukherji, P., Avachat, S., Chitnis, A., Deodhar, N., & Godse, P. (2024). Comparative analysis of efficient implementation of CNN on CPU and GPU for image processing. International Journal of Microsystems and IoT, 2(2), 538–547. https://doi.org/10.5281/zenodo.10792152
Rakhmadi, A., & Ariyanto, R. (2021). Measurement motoric system of cerebral palsy disability using gross motor function measure (GMFM). Khazanah Informatika, 7(1), 32–37.
Rakhmadi, A., Yudhana, A., & Sunardi, S. (2024). Virtual reality and augmented reality in sign language recognition: A review of current approaches. International Journal of Informatics and Computation, 6(2). https://doi.org/10.35842/ijicom
Rasch, M. J., Mackin, C., Le Gallo, M., Chen, A., Fasoli, A., Odermatt, F., Li, N., Nandakumar, S. R., Narayanan, P., Tsai, H., Burr, G. W., Sebastian, A., & Narayanan, V. (2023). Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators. Nature Communications, 14(1). https://doi.org/10.1038/s41467-023-40770-4
Rawal, V., Prajapati, P., & Darji, A. (2023). Hardware implementation of 1D-CNN architecture for ECG arrhythmia classification. Biomedical Signal Processing and Control, 85, 104865. https://doi.org/10.1016/j.bspc.2023.104865
Rico, M.-U.-K. (2023). Performance analysis of CNN model for image classification with Intel OpenVINO on CPU and GPU [Thesis]. University of Windsor.
Safitri, M., Yuniarno, E. M., & Rachmadi, R. F. (2024). Indonesian sign language (SIBI) recognition and extraction using CNN-symmetric deletion spelling correction. ISITIA 2024, 220–225. https://doi.org/10.1109/ISITIA63062.2024.10667714
Saha, A., Rahman, M., & Wu, F. (2025). Benchmarking CPU vs GPU on LSTM model using groundwater dataset. SoutheastCon 2025, 1318–1319. https://doi.org/10.1109/SoutheastCon56624.2025.10971639
Salcedo-Navarro, A., Gutierrez-Aguado, J., & Garcia-Pineda, M. (2025). UHD video encoding in CPU versus GPU: Quality and performance trade-offs. IEEE Access, 13, 55115–55129. https://doi.org/10.1109/ACCESS.2025.3553634
Schulder, M., Bigeard, S., Hanke, T., & Kopf, M. (2023). The sign language interchange format: Harmonising sign language datasets for computational processing. ICASSPW 2023, 1–5. https://doi.org/10.1109/ICASSPW59220.2023.10193022
Siek, M. (2023). Benchmarking CPU vs GPU performance in building predictive LSTM deep learning models. AIP Conference Proceedings, 2510(1), 030017. https://doi.org/10.1063/5.0128638
Staka, Z., Misic, M., & Tomasevic, M. (2025). CPU vs GPU: Performance evaluation of classical machine and deep learning algorithms. INFOTEH 2025, 1–6. https://doi.org/10.1109/INFOTEH64129.2025.10959248
Subandi, R., H., & Yudhana, A. (2024). Pneumonia medical image classification using AlexNet and GoogleNet. International Journal of Computing and Digital Systems, 16(1), 1675–1684. https://doi.org/10.12785/ijcds/1601124
Subburaj, S., & Murugavalli, S. (2022). Survey on sign language recognition in context of vision-based and deep learning. Measurement: Sensors, 23. https://doi.org/10.1016/j.measen.2022.100385
Subramanian, B., Olimov, B., Naik, S. M., Kim, S., Park, K. H., & Kim, J. (2022). An integrated MediaPipe-optimized GRU model for Indian sign language recognition. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-15998-7
Suharjito, Thiracitta, N., & Gunawan, H. (2021). SIBI sign language recognition using CNN combined with transfer learning. Procedia Computer Science, 179, 72–80. https://doi.org/10.1016/j.procs.2020.12.011
Sultan, A., Makram, W., Kayed, M., & Ali, A. A. (2022). Sign language identification and recognition: A comparative study. Open Computer Science, 12(1), 191–210. https://doi.org/10.1515/comp-2022-0240
Svendsen, B., & Kadry, S. (2023). Comparative analysis of image classification models for Norwegian sign language recognition. Technologies, 11(4). https://doi.org/10.3390/technologies11040099
Tang, X., Chang, X., Chen, N., Ni, Y. (MaoMao), LC, R. A. Y., & Tong, X. (2023). Community-driven information accessibility: Online sign language content creation within d/Deaf communities. CHI 2023. https://doi.org/10.1145/3544548.3581286
Tarek, H., Aly, H., Eisa, S., & Abul-Soud, M. (2022). Optimized deep learning algorithms for tomato leaf disease detection with hardware deployment. Electronics, 11(1). https://doi.org/10.3390/electronics11010140
Tasnim, T., Rahman, M., & Wu, F. (2024). A comparative analysis of CPU and GPU-based cloud platforms for CNN binary classification. IARIA Congress 2024. https://www.thinkmind.org
Waluyo, W. N., Isnanto, R. R., & Rochim, A. F. (2023). Comparison of Mycobacterium tuberculosis image detection accuracy using CNN and CNN-KNN. Jurnal RESTI, 7(1), 80–87. https://doi.org/10.29207/resti.v7i1.4626
Wijaya, F., Dahendra, L., Purwanto, E. S., & Ario, M. K. (2024). Quantitative analysis of sign language translation using artificial neural network model. Procedia Computer Science, 245, 998–1009. https://doi.org/10.1016/j.procs.2024.10.328
Wu, X., Feng, Y., Xu, H., Lin, Z., Chen, T., Li, S., Qiu, S., Liu, Q., Ma, Y., & Zhang, S. (2023). CTransCNN: Combining transformer and CNN in multilabel medical image classification. Knowledge-Based Systems, 281. https://doi.org/10.1016/j.knosys.2023.111030
Yang, D., Li, J., Hao, G., Chen, Q., Wei, X., Dai, Z., Hou, Z., Zhang, L., & Li, X. (2024). Hardware accelerator for high accuracy sign language recognition with residual network based on FPGAs. IEICE Electronics Express, 21(4). https://doi.org/10.1587/elex.21.20230579
Zaitsev, D. A., Ajima, Y., Bartlett, J. F. C., & Kumar, A. (2025). 3D multicore CPU vs GPU on sparse patterns of Sleptsov net virtual machine. International Journal of Parallel, Emergent and Distributed Systems. https://doi.org/10.1080/17445760.2025.2490148
Zhang, Y., Pandey, D., Wu, D., Kundu, T., Li, R., & Shu, T. (2023). Accuracy-constrained efficiency optimization and GPU profiling of CNN inference for detecting drainage crossing locations. SC’23 Workshops, 1780–1788. https://doi.org/10.1145/3624062.3624260
Zhang, Z., Gao, J., Dhaliwal, R. S., & Li, T. J.-J. (2023). VISAR: A human-AI argumentative writing assistant. UIST 2023. https://doi.org/10.1145/3586183.3606800
CITEDNESS IN SCOPUS
CITEDNESS IN WOS
