Journal of Engineering in Industrial Research

h-index: 18     i10-index: 25

Statistical Validation of GRMobiNet: A Lightweight Deep Neural Network Surpassing MobileNetV2 in Classification Accuracy

Document Type : Original Research Article

Authors

Raafi Careem 1
Md Gapar MD Johar 2
Ali Khatibi 3

1 School of Graduate Studies, Postgraduate Centre ,Management and Science University, Shah Alam, Selangor, Malaysia

2 Software Engineering and Digital Innovation Centre, Management and Science University, Shah Alam, Malaysia

3 Postgraduate Center, Management and Science University, Shah Alam, Malaysia

https://doi.org/10.48309/jeires.2025.530840.1246
Abstract
This study presents a statistical evaluation of GRMobiNet, a novel lightweight deep neural network model designed for efficient image classification in resource-constrained environments (RCEs). Built upon the MobileNet architecture, GRMobiNet introduces targeted modifications to enhance predictive accuracy without increasing model size and computational complexity. To validate the performance gains, a series of controlled experiments were conducted using a custom dataset comprising ten image categories, with each model evaluated across ten repeated runs on identical test sets. A paired samples t-test was applied to compare the classification accuracy of GRMobiNet and MobileNetV2 under identical experimental conditions. Results indicate that GRMobiNet achieved a mean accuracy of 80%, significantly outperforming MobileNetV2’s 57%, with a mean improvement of 2.3 correctly predicted images per run. The observed p-value of 0.019 confirms statistical significance at the 95% confidence level. Moreover, GRMobiNet exhibited lower variance and a reduced standard error of the mean, indicating greater stability across trials. These findings confirm that GRMobiNet offers not only computational efficiency, but also statistically validated performance superiority, making it highly suitable for real-world deployment in domains such as mobile diagnostics, precision agriculture, and embedded surveillance systems. The statistical rigor of this validation underscores GRMobiNet’s robustness and reliability as an advancement over existing lightweight architectures.

Graphical Abstract

Statistical Validation of GRMobiNet: A Lightweight Deep Neural Network Surpassing MobileNetV2 in Classification Accuracy

Keywords

Deep neural networks
GRMobiNet
Image classification
MobileNet
Resource constrained environment
t- test

Subjects

OPEN ACCESS

©2025 The author(s). This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit: http://creativecommons.org/licenses/by/4.0/

[1]. H.-I. Liu, M. Galindo, H. Xie, L.-K. Wong, H.-H. Shuai, Y.-H. Li, W.-H. Cheng, Lightweight deep learning for resource-constrained environments: A survey, ACM Computing Surveys, 2024, 56, 1-42. [Crossref], [Google Scholar], [Publisher]
[2]. Y. Zhong, Z. Teng, M. Tong, LightMixer: A novel lightweight convolutional neural network for tomato disease detection, Frontiers in plant science, 2023, 14, 1166296. [Crossref], [Google Scholar], [Publisher]
[3]. H.K. Kondaveeti, V.K. Vatsavayi, S. Mangapathi, R.M. Yasaswini, Lightweight deep learning: introduction, advancements, and applications, advancement in business analytics tools for higher financial performance, IGI Global Scientific Publishing, 2023, 242-259. [Google Scholar], [Publisher]
[4]. L. Zhao, L. Wang, Y. Jia, Y. Cui, A lightweight deep neural network with higher accuracy, Plos one, 2022, 17, e0271225. [Crossref], [Google Scholar], [Publisher]
[5]. Y. Yang, H. Wang, R. Jiang, X. Guo, J. Cheng, Y. Chen, A review of IoT-enabled mobile healthcare: technologies, challenges, and future trends, IEEE Internet of Things Journal, 2022, 9, 9478-9502. [Crossref], [Google Scholar], [Publisher]
[6]. A. Singh, S.C. Satapathy, A. Roy, A. Gutub, Ai-based mobile edge computing for iot: Applications, challenges, and future scope, Arabian Journal for Science and Engineering, 2022, 47, 9801-9831. [Crossref], [Google Scholar], [Publisher]
[7]. H. Hussain, P. Tamizharasan, C. Rahul, Design possibilities and challenges of DNN models: a review on the perspective of end devices, Artificial Intelligence Review, 2022, 55, 5109-5167. [Crossref], [Google Scholar], [Publisher]
[8]. L. Alzubaidi, J. Zhang, A.J. Humaidi, A. Al-Dujaili, Y. Duan, O. Al-Shamma, J. Santamaría, M.A. Fadhel, M. Al-Amidie, L. Farhan, Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, Journal of big Data, 2021, 8, 53. [Crossref], [Google Scholar], [Publisher]
[9]. F. Jauro, H. Chiroma, A.Y. Gital, M. Almutairi, S.i.M. Abdulhamid, J.H. Abawajy, Deep learning architectures in emerging cloud computing architectures: Recent development, challenges and next research trend, Applied Soft Computing, 2020, 96, 106582. [Crossref], [Google Scholar], [Publisher]
[10]. R. Baron, H. Haick, Mobile diagnostic clinics, ACS sensors, 2024, 9, 2777-2792. [Crossref], [Google Scholar], [Publisher]
[11]. E. Osei, T.P. Mashamba-Thompson, Mobile health applications for disease screening and treatment support in low-and middle-income countries: A narrative review, Heliyon, 2021, 7. [Google Scholar], [Publisher]
[12]. J. Mendoza-Bernal, A. González-Vidal, A.F. Skarmeta, A convolutional neural network approach for image-based anomaly detection in smart agriculture, Expert Systems with Applications, 2024, 247, 123210. [Crossref], [Google Scholar], [Publisher]
[13]. A.M. Mishra, S. Harnal, V. Gautam, R. Tiwari, S. Upadhyay, Weed density estimation in soya bean crop using deep convolutional neural networks in smart agriculture, Journal of Plant Diseases and Protection, 2022, 129, 593-604. [Crossref], [Google Scholar], [Publisher]
[14]. V. Dhanya, A. Subeesh, N. Kushwaha, D.K. Vishwakarma, T.N. Kumar, G. Ritika, A. Singh, Deep learning based computer vision approaches for smart agricultural applications, Artificial Intelligence in Agriculture, 2022, 6, 211-229. [Crossref], [Google Scholar], [Publisher]
[15]. M. Altalak, M. Ammad uddin, A. Alajmi, A. Rizg, Smart agriculture applications using deep learning technologies: A survey, Applied Sciences, 2022, 12, 5919. [Crossref], [Google Scholar], [Publisher]
[16]. J. Alfred Daniel, C. Chandru Vignesh, B.A. Muthu, R. Senthil Kumar, C. Sivaparthipan, C.E.M. Marin, Fully convolutional neural networks for LIDAR–camera fusion for pedestrian detection in autonomous vehicle, Multimedia Tools and Applications, 2023, 82, 25107-25130. [Crossref], [Google Scholar], [Publisher]
[17]. F. Martinez, H. Montiel, F. Martinez, Comparative study of optimization algorithms on convolutional network for autonomous driving, International Journal of Electrical and Computer Engineering, 2022, 12, 6363. [Crossref], [Google Scholar], [Publisher]
[18]. L. Chen, S. Lin, X. Lu, D. Cao, H. Wu, C. Guo, C. Liu, F.-Y. Wang, Deep neural network based vehicle and pedestrian detection for autonomous driving: A survey, IEEE Transactions on Intelligent Transportation Systems, 2021, 22, 3234-3246. [Crossref], [Google Scholar], [Publisher]
[19]. S. Grigorescu, B. Trasnea, T. Cocias, G. Macesanu, A survey of deep learning techniques for autonomous driving, Journal of field robotics, 2020, 37, 362-386. [Crossref], [Google Scholar], [Publisher]
[20]. A. Shabbir, N. Arshad, S. Rahman, M.A. Sayem, F. Chowdhury, Analyzing surveillance videos in real-time using AI-powered deep learning techniques, International Journal on Recent and Innovation Trends in Computing and Communication, 2024, 12, 950-960. [Google Scholar], [Publisher]
[21]. C. Fontes, E. Hohma, C.C. Corrigan, C. Lütge, AI-powered public surveillance systems: why we (might) need them and how we want them, Technology in Society, 2022, 71, 102137. [Crossref], [Google Scholar], [Publisher]
[22]. M.J. Iqbal, M.M. Iqbal, I. Ahmad, M.O. Alassafi, A.S. Alfakeeh, A. Alhomoud, Real‐time surveillance using deep learning, Security and Communication Networks, 2021, 2021, 6184756. [Crossref], [Google Scholar], [Publisher]
[23]. M.P. Kumar, D. Hasmitha, B. Usha, B. Jyothsna, D. Sravya, Brain tumor classification using mobilenet, 2024 international conference on integrated circuits and communication systems (ICICACS), IEEE, 2024, 1-7. [Crossref], [Google Scholar], [Publisher]
[24]. T.H. Arfan, M. Hayaty, A. Hadinegoro, Classification of brain tumours types based on MRI images using mobilenet, 2021 2nd International Conference on Innovative and Creative Information Technology (ICITech), IEEE, 2021, 69-73. [Crossref], [Google Scholar], [Publisher]
[25]. M.A.B. Abbass, Y. Ban, MobileNet-based architecture for distracted human driver detection of autonomous cars, Electronics, 2024, 13, 2 , 365. [Crossref], [Google Scholar], [Publisher]
[26]. D. Sinha, M. El-Sharkawy, Thin mobilenet: An enhanced mobilenet architecture, 2019 IEEE 10th annual ubiquitous computing, electronics & mobile communication conference (UEMCON), IEEE, 2019, 0280-0285. [Crossref], [Google Scholar], [Publisher]
[27]. A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv:1704.04861, 2017. [Crossref], [Google Scholar], [Publisher]
[28]. T. Magadza, S. Viriri, Brain tumor segmentation using partial depthwise separable convolutions, IEEE Access, 2022, 10, 124206-124216. [Crossref], [Google Scholar], [Publisher]
[29]. S.-F. Hsiao, B.-C. Tsai, Efficient computation of depthwise separable convolution in MoblieNet deep neural network models, 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), IEEE, 2021, 1-2. [Crossref], [Google Scholar], [Publisher]
[30]. F. Chollet, Xception: Deep learning with depthwise separable convolutions, Proceedings of the IEEE conference on computer vision and Pattern Recognition, 2017, 1251-1258. [Google Scholar], [Publisher]
[31]. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.C. Chen, Mobilenetv2: Inverted residuals and linear bottlenecks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, 4510-4520. [Google Scholar], [Publisher]
[32]. C. Lin, P. Yang, Q. Wang, Z. Qiu, W. Lv, Z. Wang, Efficient and accurate compound scaling for convolutional neural networks, Neural Networks, 2023, 167, 787-797. [Crossref], [Google Scholar], [Publisher]
[33]. S.J. Colaco, D.S. Han, Deep learning-based facial landmarks localization using compound scaling, IEEE Access, 2022, 10, 7653-7663. [Crossref], [Google Scholar], [Publisher]
[34]. M.F. Hashmi, S. Katiyar, A.W. Hashmi, A.G. Keskar, Pneumonia detection in chest X-ray images using compound scaled deep learning model, Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i komunikacije, 2021, 62, 397-406. [Crossref], [Google Scholar], [Publisher]
[35]. T. Liang, J. Glossner, L. Wang, S. Shi, X. Zhang, Pruning and quantization for deep neural network acceleration: A survey, Neurocomputing, 2021, 461, 370-403. [Crossref], [Google Scholar], [Publisher]
[36]. H.F. Langroudi, V. Karia, Z. Carmichael, A. Zyarah, T. Pandit, J.L. Gustafson, D. Kudithipudi, Alps: Adaptive quantization of deep neural networks with generalized posits,  Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, 3100-3109. [Google Scholar], [Publisher]
[37]. Y. Zhou, S.-M. Moosavi-Dezfooli, N.-M. Cheung, P. Frossard, Adaptive quantization for deep neural network,  Proceedings of the AAAI Conference on Artificial Intelligence, 2018. [Crossref], [Google Scholar], [Publisher]
[38]. A. Polino, R. Pascanu, D. Alistarh, Model compression via distillation and quantization, arXiv preprint arXiv:1802.05668, 2018. [Crossref], [Google Scholar], [Publisher]
[39]. O.G. Atanda, W. Ismaila, A.O. Afolabi, O.A. Awodoye, A.S. Falohun, J.P. Oguntoye, Statistical Analysis of a deep learning based trimodal biometric system using paired sampling T-Test,  2023 International Conference on Science, Engineering and Business for Sustainable Development Goals (SEB-SDG), IEEE, 2023, 1-10. [Crossref], [Google Scholar], [Publisher]
[40]. S. Afifah, A. Mudzakir, A.B.D. Nandiyanto, How to calculate paired sample t-test using SPSS software: From step-by-step processing for users to the practical examples in the analysis of the effect of application anti-fire bamboo teaching materials on student learning outcomes, Indonesian Journal of Teaching in Science, 2022, 2, 81-92. [Crossref], [Google Scholar], [Publisher]
[41]. R. Careem, G. Md Johar, A. Khatibi, Analyzing baseline models for optimizing deep neural networks in resource-constrained environments, Journal of Engineering in Industrial Research, 2024, 5, 2, 81–89. [Crossref], [Google Scholar], [Publisher]
[42]. R. Careem, M. Gapar Md Johar, A. Khatibi, Baseline model for deep neural networks in resource-constrained environments: an empirical investigation, International Journal of Computing and Digital Systems, 2024, 16, 1147-1161. [Crossref], [Google Scholar], [Publisher]
[43]. R. Careem, G. Johar, A. Khatibi, Deep neural networks optimization for resource-constrained environments: techniques and models, Indonesian Journal of Electrical Engineering and Computer Science, 2024, 33, 1843-1854. [Crossref], [Google Scholar], [Publisher]
[44]. A. Jayasimhan, P. Pabitha, A comparison between CPU and GPU for image classification using Convolutional Neural Networks, 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), IEEE, 2022, 1-4. [Crossref], [Google Scholar], [Publisher]
[45]. H. Kimm, I. Paik, H. Kimm, Performance comparison of TPU, GPU, CPU on Google Colaboratory over distributed deep learning, Proceedings of the 2021 IEEE 14th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC), 2021, 312–319. [Crossref], [Google Scholar], [Publisher]
[46]. U.K.B. Dubey, D.P. Kothari, Research Methodology: Techniques and Trends (1st ed.), Chapman and Hall/CRC, 2022. [Crossref], [Google Scholar], [Publisher]
[47]. H. Chen, G. Zhou, W. He, X. Duan, H. Jiang, Classification and identification of agricultural products based on improved MobileNetV2, Scientific Reports, 2024, 14, 3454. [Crossref], [Google Scholar], [Publisher]
[48]. L. Dang, P. Pang, J. Lee, Depth-wise separable convolution neural network with residual connection for hyperspectral image classification, Remote Sensing, 2020, 12, 3408. [Crossref], [Google Scholar], [Publisher]
[49]. S. Benkrama, N.E.H. Hemdani, Deep Learning with EfficientNetB1 for detecting brain tumors in MRI images,  2023 International Conference on Advances in Electronics, Control and Communication Systems (ICAECCS), IEEE, 2023, 1-6. [Crossref], [Google Scholar], [Publisher]
[50]. B. Espejo-Garcia, I. Malounas, N. Mylonas, A. Kasimati, S. Fountas, Using EfficientNet and transfer learning for image-based diagnosis of nutrient deficiencies, Computers and Electronics in Agriculture, 2022, 196, 106868. [Crossref], [Google Scholar], [Publisher]
[51]. M. Tan, Q. Le, Efficientnetv2: Smaller models and faster training, International Conference on Machine Learning, PMLR, 2021, 10096-10106. [Google Scholar], [Publisher]
[52]. V.T. Hoang, K.-H. Jo, Practical analysis on architecture of EfficientNet, 2021 14th International Conference on Human System Interaction (HSI), IEEE, 2021, 1-4. [Crossref], [Google Scholar], [Publisher]
[53]. G. Habib, S. Qureshi, GAPCNN with HyPar: Global Average Pooling convolutional neural network with novel NNLU activation function and HYBRID parallelism, Frontiers in Computational Neuroscience, 2022, 16, 1004988. [Crossref], [Google Scholar], [Publisher]
[54]. A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, Advances in neural information processing systems, 2012, 25. [Google Scholar], [Publisher]
[55]. H.A. Al-Jubouri, S.M. Mahmmod, A comparative analysis of automatic deep neural networks for image retrieval, TELKOMNIKA (Telecommunication Computing Electronics and Control), 2021, 19, 858-871. [Crossref], [Google Scholar], [Publisher]
[56]. L. Xu, S. Qiu, B. Yuan, J. Jiang, C. Renggli, S. Gan, K. Kara, G. Li, J. Liu, W. Wu, Stochastic gradient descent without full data shuffle: with applications to in-database machine learning and deep learning systems, The VLDB Journal, 2024, 33, 1231-1255. [Crossref], [Google Scholar], [Publisher]
Journal of Engineering in Industrial Research
Volume 6, Issue 4
Summer 2025
Pages 310-323

  • Receive Date 21 June 2025
  • Revise Date 21 July 2025
  • Accept Date 05 August 2025

Home

A-Z Journals

Indexing and Abstracting

Editorial Board

Guide for Authors

Submit Manuscript

Contact Us