{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:13:13Z","timestamp":1763017993960,"version":"build-2065373602"},"reference-count":41,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2019,2,13]],"date-time":"2019-02-13T00:00:00Z","timestamp":1550016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Deep learning solutions are being increasingly used in mobile applications. Although there are many open-source software tools for the development of deep learning solutions, there are no guidelines in one place in a unified manner for using these tools toward real-time deployment of these solutions on smartphones. From the variety of available deep learning tools, the most suited ones are used in this paper to enable real-time deployment of deep learning inference networks on smartphones. A uniform flow of implementation is devised for both Android and iOS smartphones. The advantage of using multi-threading to achieve or improve real-time throughputs is also showcased. A benchmarking framework consisting of accuracy, CPU\/GPU consumption, and real-time throughput is considered for validation purposes. The developed deployment approach allows deep learning models to be turned into real-time smartphone apps with ease based on publicly available deep learning and smartphone software tools. This approach is applied to six popular or representative convolutional neural network models, and the validation results based on the benchmarking metrics are reported.<\/jats:p>","DOI":"10.3390\/make1010027","type":"journal-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T03:21:46Z","timestamp":1550114506000},"page":"450-465","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps"],"prefix":"10.3390","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7128-6438","authenticated-orcid":false,"given":"Abhishek","family":"Sehgal","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX 75080, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5183-6359","authenticated-orcid":false,"given":"Nasser","family":"Kehtarnavaz","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX 75080, USA"}]}],"member":"1968","published-online":{"date-parts":[[2019,2,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"ref_2","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Adv. Neural Inf. Process. Syst., 1\u20139."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Deng, L., Li, J., Huang, J.T., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, X., and Williams, J. (2013, January 26\u201331). Recent advances in deep learning for speech research at Microsoft. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada.","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"ref_5","unstructured":"(2018, September 15). Number of Smartphone Users Worldwide 2014\u20132020. Available online: https:\/\/www.statista.com\/statistics\/330695\/number-of-smartphone-users-worldwide\/."},{"key":"ref_6","unstructured":"(2018, July 11). Arduino. Available online: https:\/\/www.arduino.cc\/."},{"key":"ref_7","unstructured":"(2018, July 11). Raspberry Pi. Available online: https:\/\/www.raspberrypi.org\/."},{"key":"ref_8","first-page":"1","article-title":"PupilScreen: Using Smartphones to Assess Traumatic Brain Injury","volume":"1","author":"Mariakakis","year":"2017","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_9","first-page":"1","article-title":"BiliScreen: Scleral Jaundice Detection with a Smartphone","volume":"1","author":"Mariakakis","year":"2017","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_10","unstructured":"Chu, L., Qiu, R., Liu, H., Ling, Z., Zhang, T., and Wang, J. (arXiv, 2017). Individual Recognition in Schizophrenia using Deep Learning Methods with Random Forest and Voting Classifiers: Insights from Resting State EEG Streams, arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"9017","DOI":"10.1109\/ACCESS.2018.2800728","article-title":"A Convolutional Neural Network Smartphone App for Real-Time Voice Activity Detection","volume":"6","author":"Sehgal","year":"2018","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lane, N.D., Bhattacharya, S., Georgiev, P., Forlivesi, C., Jiao, L., Qendro, L., and Kawsar, F. (2016, January 11\u201314). DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices. Proceedings of the 15th International Conference on Information Processing in Sensor Networks (IPSN \u201916), Vienna, Austria.","DOI":"10.1109\/IPSN.2016.7460664"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MPRV.2017.2940968","article-title":"Squeezing Deep Learning into Mobile and Embedded Devices","volume":"16","author":"Lane","year":"2017","journal-title":"IEEE Pervasive Comput."},{"key":"ref_14","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (arXiv, 2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, arXiv."},{"key":"ref_15","unstructured":"Han, S., Mao, H., and Dally, W.J. (arXiv, 2015). Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding, arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. (arXiv, 2014). Caffe: Convolutional Architecture for Fast Feature Embedding, arXiv.","DOI":"10.1145\/2647868.2654889"},{"key":"ref_17","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (arXiv, 2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, arXiv."},{"key":"ref_18","unstructured":"(2018, July 11). PyTorch. Available online: https:\/\/pytorch.org\/."},{"key":"ref_19","unstructured":"(2018, July 11). Microsoft Cognitive Toolkit. Available online: https:\/\/www.microsoft.com\/en-us\/cognitive-toolkit\/."},{"key":"ref_20","unstructured":"(2018, July 11). Keras. Available online: https:\/\/keras.io\/."},{"key":"ref_21","unstructured":"(2018, July 11). Core ML. Available online: https:\/\/developer.apple.com\/documentation\/coreml."},{"key":"ref_22","unstructured":"(2018, July 11). Coremltools. Available online: https:\/\/apple.github.io\/coremltools\/."},{"key":"ref_23","unstructured":"(2018, July 12). tf-coreml: TensorFlow to CoreML Converter. Available online: https:\/\/github.com\/tf-coreml\/tf-coreml."},{"key":"ref_24","unstructured":"(2018, July 12). Deep-Learning-Model-Convertor: The Convertor\/Conversion of Deep Learning Models for Different Deep Learning Frameworks\/Softwares. Available online: https:\/\/github.com\/ysh329\/deep-learning-model-convertor."},{"key":"ref_25","unstructured":"(2018, August 11). Gradle Build Dependencies for Android Studio. Available online: https:\/\/developer.android.com\/studio\/build\/dependencies."},{"key":"ref_26","unstructured":"(2018, July 11). Mobile Operating System Market Share. Available online: http:\/\/gs.statcounter.com\/os-market-share\/mobile\/worldwide."},{"key":"ref_27","unstructured":"(2018, July 11). Android Studio. Available online: https:\/\/developer.android.com\/studio\/."},{"key":"ref_28","unstructured":"(2018, July 11). Xcode. Available online: https:\/\/developer.apple.com\/xcode\/."},{"key":"ref_29","unstructured":"(2018, July 11). MNIST handwritten digit database. Available online: http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., and Bernstein, M. (arXiv, 2014). ImageNet Large Scale Visual Recognition Challenge, arXiv.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/35.41400","article-title":"Handwritten digit recognition: applications of neural network chips and automatic learning","volume":"27","author":"Jackel","year":"1989","journal-title":"IEEE Commun. Mag."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (arXiv, 2015). Deep Residual Learning for Image Recognition, arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (arXiv, 2015). Rethinking the Inception Architecture for Computer Vision, arXiv.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 8\u201310). Going deeper with convolutions. Proceedings of the IEEE Conference on on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_35","unstructured":"Ioffe, S., and Szegedy, C. (arXiv, 2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, arXiv."},{"key":"ref_36","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (arXiv, 2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size, arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (arXiv, 2016). Densely Connected Convolutional Networks, arXiv.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_38","unstructured":"Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (arXiv, 2014). How transferable are features in deep neural networks?, arXiv."},{"key":"ref_39","unstructured":"(2018, August 11). Android Profiler for Android Studio. Available online: https:\/\/developer.android.com\/studio\/profile\/android-profiler."},{"key":"ref_40","unstructured":"(2018, August 11). Instruments for Xcode IDE. Available online: https:\/\/help.apple.com\/instruments\/mac\/current\/."},{"key":"ref_41","unstructured":"(2018, August 11). Android\u2014OpenCV library. Available online: https:\/\/opencv.org\/platforms\/android\/."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/1\/1\/27\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:31:55Z","timestamp":1760185915000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/1\/1\/27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,13]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,3]]}},"alternative-id":["make1010027"],"URL":"https:\/\/doi.org\/10.3390\/make1010027","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2019,2,13]]}}}