An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Embedded systems technology is undergoing a phase of transformation owing to the novel advancements in computer architecture and the breakthroughs in machine learning applications. The areas of applications of embedded machine learning (EML) include accurate computer vision schemes, reliable speech recognition, innovative healthcare, robotics, and more. However, there exists a critical drawback in the efficient implementation of ML algorithms targeting embedded applications. Machine learning algorithms are generally computationally and memory intensive, making them unsuitable for resource-constrained environments such as embedded and mobile devices. In order to efficiently implement these compute and memory-intensive algorithms within the embedded and mobile computing space, innovative optimization techniques are required at the algorithm and hardware levels. To this end, this survey aims at exploring current research trends within this circumference. First, we present a brief overview of compute intensive machine learning algorithms such as hidden Markov models (HMM), k-nearest neighbors (k-NNs), support vector machines (SVMs), Gaussian mixture models (GMMs), and deep neural networks (DNNs). Furthermore, we consider different optimization techniques currently adopted to squeeze these computational and memory-intensive algorithms within resource-limited embedded and mobile environments. Additionally, we discuss the implementation of these algorithms in microcontroller units, mobile devices, and hardware accelerators. Conclusively, we give a comprehensive overview of key application areas of EML technology, point out key research directions and highlight key take-away lessons for future research exploration in the embedded machine learning domain.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1707.01083 · Cited by 9,982
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00716 · Cited by 9,982
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319 · cited 1×
“Besides, the recent breakthroughs of deep learning models in application areas such as computer vision [3–7], speech recognition [8,9], language translation, and processing [10,11], robotics, and healthcare [12] make this overlap a key research direction for the development of next-generation embedded devices.”
BackgroundAn introduction to hidden Markov models
Rabiner, L., & Juang, B. (1986) · IEEE ASSP Magazine · doi:10.1109/massp.1986.1165342 · Cited by 4,775
Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158 · cited 6×
“Also, hardware design-based optimizations such as Tiling and data reuse may be utilized [25].”
MethodInfluentialNeural Networks: Tricks of the Trade: Second Edition
(2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8 · Cited by 2,116
Deep Learning With Edge Computing: A Review
Chen, J., & Ran, X. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2921977 · Cited by 1,540 · cited 1×
“Jiasi and Xukan [33], in their review, explored deep learning concepts, narrowing down on inference at end devices but do not compare different embedded chipset architectures to inform which architecture or optimization is appropriate for the different DNN models.”
BackgroundLearning both Weights and Connections for Efficient Neural Networks
Han, S., Pool, J., Tran, J., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1506.02626 · Cited by 1,481 · cited 6×
“function of the Arithmetic Precision adopted for a single MAC unit in a 45 nm CMOS [124].”
BackgroundMethodInfluentialDeep Learning with Limited Numerical Precision
Gupta, S., Agrawal, A., Gopalakrishnan, K., & Narayanan, P. (2015) · arXiv · doi:10.48550/arxiv.1502.02551 · Cited by 1,364 · cited 1×
“Additionally, [167] considers training a deep network using 16-bit fixed-point arithmetic with stochastic rounding to minimize accuracy loss.”
BackgroundRSVM: Reduced Support Vector Machines
Lee, Y.-J., & Mangasarian, O. L. (2001) · Proceedings of the 2001 SIAM International Conference on Data Mining · doi:10.1137/1.9781611972719.13 · Cited by 647 · cited 1×
“[100] Reduced SVM In this work, a Smoothing Algorithm is proposed to solve the QP problem.”
MethodDeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
Lane, N. D., Bhattacharya, S., Georgiev, P., Forlivesi, C., Jiao, L., Qendro, L., & Kawsar, F. (2016) · 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn.2016.7460664 · Cited by 450
Training deep neural networks with low precision multiplications
Courbariaux, M., Bengio, Y., & David, J.-P. (2014) · arXiv · doi:10.48550/arxiv.1412.7024 · Cited by 407
TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities
Sanchez-Iborra, R., & Skarmeta, A. F. (2020) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2020.3005467 · Cited by 295 · cited 13×
“TinyML is a machine learning technique that integrates compressed and optimized machine learning to suit very low-power MCUs [141].”
BackgroundMethodInfluentialBanbury, C., Zhou, C., Fedorov, I., Navarro, R. M., Thakker, U., Gope, D., Reddi, V. J., Mattina, M., & Whatmough, P. N. (2020) · arXiv · doi:10.48550/arxiv.2010.11267 · Cited by 183
Adaptive deep learning model selection on embedded systems
Taylor, B., Marco, V. S., Wolff, W., Elkhatib, Y., & Wang, Z. (2018) · Proceedings of the 19th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems · doi:10.1145/3211332.3211336 · Cited by 90 · cited 2×
“2018 [74] Image Processing This research investigates an adaptive machine learning approach to selecting the most optimal DNN for a given input, thereby saving inference time.”
MethodAn intelligent smartphone based approach using IoT for ensuring safe driving
Mamun, M. A. A., Puspo, J. A., & Das, A. K. (2017) · 2017 International Conference on Electrical Engineering and Computer Science (ICECOS) · doi:10.1109/icecos.2017.8167137 · Cited by 30 · cited 1×
“[68] k-means Smartphones Safe Driving 2017”
A Discreet Wearable Long-Range Emergency System Based on Embedded Machine Learning
Orfanidis, C., Hassen, R. B. H., Kwiek, A., Fafoutis, X., & Jacobsson, M. (2021) · 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) · doi:10.1109/percomworkshops51409.2021.9430981 · Cited by 14 · cited 1×
“Besides, the recent breakthroughs of deep learning models in application areas such as computer vision [3–7], speech recognition [8,9], language translation, and processing [10,11], robotics, and healthcare [12] make this overlap a key research direction for the development of next-generation embedded devices.”
Background
Research works printed but not linked: 146
- Krizhevsky, 2012, ImageNet classification with deep convolutional neural networks Alex, Adv. Neural Inf. Process. Syst., 25, 1097
- Szegedy, C., Liu, W., Jia, P.Y., Reed, S.S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA. · DOI · Paper page
- Real, E., Moore, S., Selle, A., Saxena, S., Suematsu, Y.L., Tan, J., Le, Q.V., and Kurakin, A. (2017, January 6–11). Large-scale evolution of image classifiers. Proceedings of the 34th International Conference Machine Learning ICML, Sydney, Australia.
- Chan, W., Jaitly, N., Le, Q.V., and Vinyals, O. (2016, January 20–25). Listen, attend and spell. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.
- Collobert, 2011, Natural language processing (almost) from scratch, J. Mach. Learn. Res., 12, 2493
- Dean, J. (2020, January 16–20). The deep learning revolution and its implications for computer architecture and chip design. Proceedings of the 2020 IEEE International Solid-State Circuits Conference-(ISSCC), San Francisco, CA, USA. · DOI · Paper page
- Cui, 2020, Seafloor habitat mapping using multibeam bathymetric and backscatter intensity multi-features SVM classification framework, Appl. Acoust., 174, 107728, 10.1016/j.apacoust.2020.107728 · doi:10.1016/j.apacoust.2020.107728
- Khan, M.A., and Kim, J. (2020). Toward developing efficient Conv-AE-based intrusion detection system using heterogeneous dataset. Electronics, 9. · DOI
- Li, P., Luo, Y., Zhang, N., and Cao, Y. (2015, January 6–7). HeteroSpark: A heterogeneous CPU/GPU spark platform for machine learning algorithms. Proceedings of the 2015 IEEE International Conference Networking, Architecture Storage, NAS, Boston, MA, USA.
- Raparti, 2018, RAPID: Memory-aware NoC for latency optimized GPGPU architectures, IEEE Trans. Multi-Scale Comput. Syst., 4, 874, 10.1109/TMSCS.2018.2871094 · doi:10.1109/tmscs.2018.2871094
- Cheng, 2019, A low-cost and energy-efficient noc architecture for GPGPUs, J. Nat. Gas Geosci., 4, 1
- Zhang, L., Cheng, X., Zhao, H., Mohanty, S.P., and Fang, J. (2019, January 11). Exploration of system configuration in effective training of CNNs on GPGPUs. Proceedings of the 2019 IEEE International Conferece Consumer Electronics ICCE, Las Vegas, NJ, USA. · DOI
- Yu, Q., Wang, C., Ma, X., Li, X., and Zhou, X. (2015, January 4–7). A deep learning prediction process accelerator based FPGA. Proceedings of the 2015 IEEE/ACM 15th International Symposium Cluster Cloud, Grid Computer CCGrid 2015, Shenzhen, China. · DOI
- Noronha, D.H., Zhao, R., Goeders, J., Luk, W., and Wilton, S.J.E. (2019, January 24–26). On-chip FPGA debug instrumentation for machine learning applications. Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, Seaside, CA, USA.
- Wang, 2016, DLAU: A scalable deep learning accelerator unit on FPGA, IEEE Trans. Comput. Des. Integr. Circuits Syst., 36, 513
- Chang, A.X.M., Martini, B., and Culurciello, E. (2021, January 15). Recurrent Neural Networks Hardware Implementationon FPGA. Available online: http://arxiv.org/abs/1511.05552. · arXiv
- Branco, S., Ferreira, A.G., and Cabral, J. (2019). Machine learning in resource-scarce embedded systems, FPGAs, and end-devices: A survey. Electronics, 8. · DOI
- Neshatpour, K., Mokrani, H.M., Sasan, A., Ghasemzadeh, H., Rafatirad, S., and Homayoun, H. (2018, January 15–19). Architectural considerations for FPGA acceleration of machine learning applications in MapReduce. Proceedings of the 18th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, Pythagorion, Greece. · doi:10.1145/3229631.3229639
- Deng, Y. (2019, January 14–18). Deep learning on mobile devices: A review. Proceedings of the SPIE 10993, Mobile Multimedia/Image Processing, Security, and Applications 2019, 109930A, Baltimore, ML, USA. · DOI
- Kim, D., Ahn, J., and Yoo, S. (2017, January 27–31). A novel zero weight/activation-aware hardware architecture of convolutional neural network. Proceedings of the 2017 Design, Automation and Test in Europe DATE 2017, Lausanne, Switzerland. · DOI
- Jawandhiya, 2018, Hardware design for machine learning, Int. J. Artif. Intell. Appl., 9, 1
- Frank, M., Drikakis, D., and Charissis, V. (2020). Machine-learning methods for computational science and engineering. Computation, 8. · DOI · Paper page
- Xiong, 2019, Deep reinforcement learning for mobile 5G and beyond: Fundamentals, applications, and challenges, IEEE Veh. Technol. Mag., 14, 44, 10.1109/MVT.2019.2903655 · DOI · Paper page
- Carbonell, 1981, Machine learning research, ACM SIGART Bull., 18, 29, 10.1145/1056743.1056744 · DOI
- Jadhav, 2016, Comparative STUDY of K-NN, naive bayes and decision tree classification techniques, Int. J. Sci. Res., 5, 1842
- (2020, December 29). Chapter 4 Logistic Regression as a Classifier. Available online: https://www.cs.cmu.edu/~kdeng/thesis/logistic.pdf.
- Salvadori, 2017, An optimisation of Gaussian mixture models for integer processing units, J. Real Time Image Process., 13, 273, 10.1007/s11554-014-0402-5 · DOI
- Das, A., Borisov, N., and Caesar, M. (2014, January 3–7). Do you hear what i hear? Fingerprinting smart devices through embedded acoustic components. Proceedings of the ACM Conference on Computer, Communication and Security, Scottsdale, AZ, USA. · DOI
- Bojinov, H., Michalevsky, Y., Nakibly, G., and Boneh, D. (2021, January 12). Mobile Device Identification via Sensor Fingerprinting. Available online: http://arxiv.org/abs/1408.1416. · arXiv
- Huynh, M., Nguyen, P., Gruteser, M., and Vu, T. (2015, January 12–16). Mobile device identification by leveraging built-in capacitive signature. Proceedings of the ACM Conference on Compututer, Communication and Security, Denver, CO, USA.
- Dhar, 2015, FPGA implementation of feature extraction based on histopathalogical image and subsequent classification by support vector machine, IJISET Int. J. Innov. Sci. Eng. Technol., 2, 744
- Yu, L., Ukidave, Y., and Kaeli, D. (2014, January 9–12). GPU-accelerated HMM for speech recognition. Proceedings of the International Conference Parallel Processing Work, Minneapolis, MN, USA. · doi:10.1109/icppw.2014.59
- Zubair, M., Yoon, C., Kim, H., Kim, J., and Kim, J. (2015, January 24–27). Smart wearable band for stress detection. Proceedings of the 2015 5th International Conference IT Converg. Secur. ICITCS, Kuala Lumpur, Malaysia. · DOI
- Razavi, A., Valkama, M., and Lohan, E.S. (2015, January 6–10). K-means fingerprint clustering for low-complexity floor estimation in indoor mobile localization. Proceedings of the 2015 IEEE Globecom Work. GC Wkshps 2015, San Diego, CA, USA. · DOI
- Bhide, V.H., and Wagh, S. (2015, January 2–4). I-learning IoT: An intelligent self learning system for home automation using IoT. Proceedings of the 2015 International Conference Communication Signalling Process. ICCSP 2015, Melmaruvathur, India. · DOI
- Munisami, 2015, Plant Leaf recognition using shape features and colour histogram with K-nearest neighbour classifiers, Proc. Comput. Sci., 58, 740, 10.1016/j.procs.2015.08.095 · doi:10.1016/j.procs.2015.08.095
- Sowjanya, K., Singhal, A., and Choudhary, C. (2015, January 12–13). MobDBTest: A machine learning based system for predicting diabetes risk using mobile devices. Proceedings of the Souvenir 2015 IEEE Int. Adv. Comput. Conference IACC 2015, Banglore, India. · doi:10.1109/iadcc.2015.7154738
- Lee, J., Stanley, M., Spanias, A., and Tepedelenlioglu, C. (2016, January 12–14). Integrating machine learning in embedded sensor systems for Internet-of-Things applications. Proceedings of the 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Limassol, Cyprus. · DOI
- Qiu, J., Wang, J., Yao, S., Guo, K., Li, B., Zhou, E., Yu, J., Tang, T., Xu, N., and Song, S. (2016, January 21–23). Going deeper with embedded FPGA platform for convolutional neural network. Proceedings of the FPGA 2016ACM/SIGDA International Symposium Field-Programmable Gate Arrays, Monterey, CA, USA. · DOI · Paper page
- Huynh, L.N., Balan, R.K., and Lee, Y. (2016, January 30). DeepSense: A GPU-based deep convolutional neural network framework on commodity mobile devices. Proceedings of the Workshop on Wearable Systems and Application Co-Located with MobiSys 2016, Singapore. · DOI · Paper page
- Tuama, A., Comby, F., and Chaumont, M. (September, January 29). Camera model identification based machine learning approach with high order statistics features. Proceedings of the 24th European Signal Processing Conference (EUSIPCO), Budapest, Hungary.
- Kurtz, 2016, Fingerprinting Mobile Devices Using Personalized Configurations, Proc. Priv. Enhanc. Technol., 1, 4
- Mohsin, M.A., and Perera, D.G. (2018, January 20–22). An FPGA-based hardware accelerator for k-nearest neighbor classification for machine learning on mobile devices. Proceedings of the ACM International Conference Proceeding Series, HEART 2018, Toronto, ON, Canada. · doi:10.1145/3241793.3241810
- Patil, S.S., and Thorat, S.A. (2016, January 12–13). Early detection of grapes diseases using machine learning and IoT. Proceedings of the 2016 Second International Conference on Cognitive Computing and Information Processing (CCIP), Mysuru, India. · DOI
- Ollander, S., Godin, C., Campagne, A., and Charbonnier, S. (2016, January 9–12). A comparison of wearable and stationary sensors for stress detection. Proceedings of the IEEE International Conference System Man, and Cybernetic SMC 2016, Budapest, Hungary. · DOI · Paper page
- Moreira, M.W.L., Rodrigues, J.J.P.C., Oliveira, A.M.B., and Saleem, K. (2016, January 11–13). Smart mobile system for pregnancy care using body sensors. Proceedings of the International Conference Sel. Top. Mob. Wirel. Networking, MoWNeT 2016, Cairo Egypt. · DOI
- Shapsough, S., Hesham, A., Elkhorazaty, Y., Zualkernan, I.A., and Aloul, F. (2016, January 14–16). Emotion recognition using mobile phones. Proceedings of the 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom), Munich, Germany. · DOI
- Hakim, 2016, Smartphone based data mining for fall detection: Analysis and design, Proc. Comput. Sci., 105, 46, 10.1016/j.procs.2017.01.188 · DOI
- Ronao, 2017, Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models, Int. J. Distrib. Sens. Netw., 13, 1, 10.1177/1550147716683687 · DOI · Paper page
- Kodali, S., Hansen, P., Mulholland, N., Whatmough, P., Brooks, D., and Wei, G.Y. (2017, January 5–8). Applications of deep neural networks for ultra low power IoT. Proceedings of the 35th IEEE International Conference on Computer Design ICCD 2017, Boston, MA, USA. · DOI
- Baldini, G., Dimc, F., Kamnik, R., Steri, G., Giuliani, R., and Gentile, C. (2017). Identification of mobile phones using the built-in magnetometers stimulated by motion patterns. Sensors, 17. · DOI
- Azimi, 2017, HiCH: Hierarchical fog-assisted computing architecture for healthcare IoT, ACM Trans. Embed. Comput. Syst., 16, 1, 10.1145/3126501 · DOI · Paper page
- Pandey, P.S. (2017, January 3–6). Machine Learning and IoT for prediction and detection of stress. Proceedings of the 17th International Conference on Computational Science and Its Applications ICCSA 2017, Trieste, Italy. · DOI
- Sneha, H.R., Rafi, M., Kumar, M.V.M., Thomas, L., and Annappa, B. (2017, January 22–24). Smartphone based emotion recognition and classification. Proceedings of the 2nd IEEE International Conference on Electrical, Computer and Communication Technology ICECCT 2017, Coimbatore, India. · DOI
- Neyja, M., Mumtaz, S., Huq, K.M.S., Busari, S.A., Rodriguez, J., and Zhou, Z. (2017, January 4–8). An IoT-based e-health monitoring system using ECG signal. Proceedings of the IEEE Global Communications Conference GLOBECOM 2017, Singapore. · doi:10.1109/glocom.2017.8255023
- Gupta, C., Suggala, A.S., Goyal, A., Simhadri, H.V., Paranjape, B., Kumar, A., Goyal, S., Udupa, R., Varma, M., and Jain, P. (2017, January 6–11). ProtoNN: Compressed and accurate kNN for resource-scarce devices. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia.
- Fafoutis, X., Marchegiani, L., Elsts, A., Pope, J., Piechocki, R., and Craddock, I. (2018, January 5–8). Extending the battery lifetime of wearable sensors with embedded machine learning. Proceedings of the IEEE World Forum on Internet Things, WF-IoT 2018, Singapore. · DOI · Paper page
- Damljanovic, A., and Lanza-Gutierrez, J.M. (2018, January 21–23). An embedded cascade SVM approach for face detection in the IoT edge layer. Proceedings of the IECON 2018—44th Annual Conference of the IEEE Industrial Electronics Society, Washington, DC, USA. · doi:10.1109/iecon.2018.8591634
- Hochstetler, J., Padidela, R., Chen, Q., Yang, Q., and Fu, S. (2018, January 25–27). Embedded deep learning for vehicular edge computing. Proceedings of the 3rd ACM/IEEE Symposium on Edge Computing SEC 2018, Seattle, WA, USA. · DOI · Paper page
- Strielkina, 2018, A markov model of healthcare internet of things system considering failures of components, CEUR Workshop Proc., 2104, 530
- Vhaduri, S., van Kessel, T., Ko, B., Wood, D., Wang, S., and Brunschwiler, T. (2019, January 10–13). Nocturnal cough and snore detection in noisy environments using smartphone-microphones. Proceedings of the IEEE International Conference on Healthcare Informatics, ICHI 2019, Xi’an, China. · DOI · Paper page
- Sattar, 2019, An IoT-based intelligent wound monitoring system, IEEE Access, 7, 144500, 10.1109/ACCESS.2019.2940622 · DOI
- Mengistu, D., and Frisk, F. (August, January 28). Edge machine learning for energy efficiency of resource constrained IoT devices. Proceedings of the Fifth International Conference on Smart Portable, Wearable, Implantable and Disabilityoriented Devices and Systems, SPWID 2019, Nice, France.
- Wang, 2019, Adaptive Federated Learning in Resource Constrained Edge Computing Systems, IEEE J. Sel. Areas Commun., 37, 1205, 10.1109/JSAC.2019.2904348 · DOI · Paper page
- Suresh, 2020, Reduction of transients in switches using embedded machine learning, Int. J. Power Electron. Drive Syst., 11, 235
- Giri, D., Chiu, K.L., di Guglielmo, G., Mantovani, P., and Carloni, L.P. (2020, January 9–13). ESP4ML: Platform-based design of systems-on-chip for embedded machine learning. Proceedings of the 2020 Design, Automation and Test in European Conference Exhibition DATE 2020, Grenoble, France. · DOI
- Tiku, 2020, A hidden markov model based smartphone heterogeneity resilient portable indoor localization framework, J. Syst. Archit., 108, 101806, 10.1016/j.sysarc.2020.101806 · DOI
- Mazlan, 2020, A smart building energy management using internet of things (IoT) and machine learning, Test. Eng. Manag., 83, 8083
- Cornetta, G., and Touhafi, A. (2021). Design and evaluation of a new machine learning framework for iot and embedded devices. Electronics, 10. · DOI
- Degirmenci, 2014, Introduction to hidden markov models, Harv. Univ., 3, 1
- 2012, Optimizing HMM speech synthesis for low-resource devices, J. Adv. Comput. Intell. Intell. Inform., 16, 327, 10.20965/jaciii.2012.p0327 · DOI
- Fu, 2011, Reducing computational and memory cost for HMM-based embedded TTS system, Commun. Comput. Inf. Sci., 224, 602
- Baoli, 2005, An improved K-nearest neighbor algorithm for text categorization, Dianzi Yu Xinxi Xuebao J. Electron. Inf. Technol., 27, 487
- Norouzi, 2012, Hamming distance metric learning, Adv. Neural Inf. Process. Syst., 2, 1061
- Saikia, J., Yin, S., Jiang, Z., Seok, M., and Seo, J.S. (2019, January 29–31). K-nearest neighbor hardware accelerator using in-memory computing SRAM. Proceedings of the 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), Lausanne, Switzerland. · DOI
- Pedersen, R., and Schoeberl, M. (2006, January 30). An embedded support vector machine. Proceedings of the 2006 International Workshop on Intelligent Solutions in Embedded Systems, Vienna, Austria. · DOI
- You, 2015, Scaling support vector machines on modern HPC platforms, J. Parallel Distrib. Comput., 76, 16, 10.1016/j.jpdc.2014.09.005 · DOI
- Boni, 2007, Low-power and low-cost implementation of SVMs for smart sensors, IEEE Trans. Instrum. Meas., 56, 39, 10.1109/TIM.2006.887319 · DOI
- Afifi, 2015, Hardware implementations of SVM on FPGA: A state-of-the-art review of current practice, Int. J. Innov. Sci. Eng. Technol., 2, 733
- Zeng, Z.Q., Yu, H.B., Xu, H.R., Xie, Y.Q., and Gao, J. (2008, January 17–19). Fast training support vector machines using parallel sequential minimal optimization. Proceedings of the 2008 3rd International Conference on Intelligent System and Knowledge Engineering, Xiamen, China.
- Anguita, 2012, Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine, Lect. Notes Comput. Sci., 7657, 216, 10.1007/978-3-642-35395-6_30 · DOI · Paper page
- Kudo, T., and Matsumoto, Y. (2001, January 2–7). Chunking with support vector machines. Proceedings of the Second Meeting of the North American Chapter of the Association for Computational Linguistics 2001, Pittsburgh, PA, USA. · DOI · Paper page
- Osuna, E., Freund, R., and Girosi, F. (1997, January 24–26). Improved training algorithm for support vector machines. Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop, Amelia Island, FL, USA.
- Anguita, D., Ghio, A., Pischiutta, S., and Ridella, S. (2007, January 12–17). A hardware-friendly support vector machine for embedded automotive applications. Proceedings of the 2007 International Joint Conference on Neural Networks, Orlando, FL, USA. · DOI
- Anguita, D., and Bozza, G. (August, January 31). The effect of quantization on support vector machines with Gaussian kernel. Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, Montreal, QC, Canada.
- Khan, F.M., Arnold, M.G., and Pottenger, W.M. (2005, January 23–26). Hardware-based support vector machine classification in logarithmic number systems. Proceedings of the 2005 IEEE International Symposium on Circuits and Systems, Kobe, Japan.
- Anguita, 2006, Feed-forward support vector machine without multipliers, IEEE Trans. Neural Netw., 17, 1328, 10.1109/TNN.2006.877537 · DOI
- Reynolds, 2009, Gaussian mixture models, Encycl. Biometr., 741, 659, 10.1007/978-0-387-73003-5_196 · DOI · Paper page
- Gorur, P., and Amrutur, B. (–2, January 30). Speeded up Gaussian mixture model algorithm for background subtraction. Proceedings of the 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Klagenfurt, Austria. · doi:10.1109/avss.2011.6027356
- Shen, Y., Hu, W., Liu, J., Yang, M., Wei, B., and Chou, C.T. (November, January ). Efficient background subtraction for real-time tracking in embedded camera networks. Proceedings of the 10th ACM Conference on Embedded Networked Sensor System, Toronto, ON, Canada.
- Johnson, 2013, Accelerating stochastic gradient descent using predictive variance reduction, Adv. Neural Inf. Process. Syst., 1, 1
- Bottou, 1991, Stochastic gradient learning in neural networks, Proc, Neuro-Nımes, 8, 1
- Li, L., Zhang, S., and Wu, J. (2018, January 27–29). An efficient hardware architecture for activation function in deep learning processor. Proceedings of the 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), Chongqing, China. · DOI
- Suda, N., Chandra, V., Dasika, G., Mohanty, A., Ma, Y., Vrudhula, S., Seo, J.S., and Cao, Y. (2016, January 21–23). Throughput-optimized OpenCL-based FPGA Accelerator for large-scale convolutional neural networks. Proceedings of the ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, Monterey, CA, USA. · DOI · Paper page
- Learning, 2017, Smartphones devices, IEEE Pervasive Comput., 16, 82
- Albawi, S., Mohammed, T.A., and Al-Zawi, S. (2017, January 21–23). Understanding of a convolutional neural network. Proceedings of the 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey. · DOI · Paper page
- O’Shea, K., and Nash, R. (2021, March 02). An Introduction to Convolutional Neural Networks. Available online: http://arxiv.org/abs/1511.08458. · arXiv
- Lawrence, 1997, Face recognition: A convolutional neural-network approach, IEEE Trans. Neural Netw., 8, 98, 10.1109/72.554195 · DOI · Paper page
- Shah, S., Haghi, B., Kellis, S., Bashford, L., Kramer, D., Lee, B., Liu, C., Andersen, R., and Emami, A. (2019, January 20–23). Decoding kinematics from human parietal cortex using neural networks. Proceedings of the 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER), San Francisco, CA, USA. · DOI
- Lee, 2017, Long short-term memory recurrent neural network-based acoustic model using connectionist temporal classification on a large-scale training corpus, Chin. Commun., 14, 23, 10.1109/CC.2017.8068761 · DOI
- Yu, 2019, A review of recurrent neural networks: LSTM cells and network architectures, Neural Comput., 31, 1235, 10.1162/neco_a_01199 · DOI · Paper page
- Khan, M.A., Karim, M.R., and Kim, Y. (2018). A two-stage big data analytics framework with real world applications using spark machine learning and long short-term memory network. Symmetry, 10. · DOI
- Jouppi, 2018, A domain-specific architecture for deep neural networks, Commun. ACM, 61, 50, 10.1145/3154484 · DOI · Paper page
- Zeiler, 2014, Visualizing and understanding convolutional networks, Lect. Notes Comput. Sci., 8689, 818, 10.1007/978-3-319-10590-1_53 · DOI · Paper page
- Khoram, S., and Li, J. (May, January 30). Adaptive quantization of neural networks. Proceedings of the 6th International Conference on Learning Representations (ICLR 2018), Vancouver, BC, Canada.
- Al-Kofahi, M.M., Al-Shorman, M.Y., and Al-Kofahi, O.M. (2019). Toward energy efficient microcontrollers and Internet-of-Things systems. Comput. Electr. Eng., 79. · doi:10.1016/j.compeleceng.2019.106457
- Li, D., Wang, X., and Kong, D. (2017, January 2–7). DeepRebirth: Accelerating deep neural network execution on mobile devices. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA. · DOI · Paper page
- Yin, H., Costa, J.A.F., and Barreto, G. (2012). A Hybrid GMM Speaker Verification System for Mobile Devices in Variable Environments. Intelligent Data Engineering and Automated Learning—IDEAL 2012, Springer. Lecture Notes in Computer Science. · DOI
- Lei, X., Senior, A., Gruenstein, A., and Sorensen, J. (2013, January 25–29). Accurate and compact large vocabulary speech recognition on mobile devices. Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH, Lyon, France. · DOI · Paper page
- Park, J., Naumov, M., Basu, P., Deng, S., Kalaiah, A., Khudia, D., Law, J., Malani, P., Malevich, A., and Nadathur, S. (2018). Deep learning inference in facebook data centers: Characterization, performance optimizations and hardware implications. arXiv.
- Capra, M., Bussolino, B., Marchisio, A., Shafique, M., Masera, G., and Martina, M. (2020). An Updated survey of efficient hardware architectures for accelerating deep convolutional neural networks. Future Internet, 12. · DOI · Paper page
- Sun, 2020, A survey of optimization methods from a machine learning perspective, IEEE Trans. Cybern., 50, 3668, 10.1109/TCYB.2019.2950779 · DOI · Paper page
- Han, S., Mao, H., and Dally, W.J. (2016, January 2–4). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. Proceedings of the 4th International Conference on Learning Representations, San Juan, Puerto Rico. Available online: https://arxiv.org/abs/1510.00149. · arXiv
- Hubara, 2018, Quantized neural networks: Training neural networks with low precision weights and activations, J. Mach. Learn. Res., 18, 1
- Tanaka, K., Arikawa, Y., Ito, T., Morita, K., Nemoto, N., Miura, F., Terada, K., Teramoto, J., and Sakamoto, T. (2020, January 19–21). Communication-efficient distributed deep learning with GPU-FPGA heterogeneous computing. Proceedings of the 2020 IEEE Symposium on High-Performance Interconnects (HOTI), Piscataway, NJ, USA. · DOI
- Lane, 2017, Squeezing deep learning into mobile and embedded devices, IEEE Pervasive Comput., 16, 82, 10.1109/MPRV.2017.2940968 · DOI · Paper page
- Gysel, P. (2021, February 20). Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks. Available online: http://arxiv.org/abs/1605.06402. · arXiv
- Moons, B., Goetschalckx, K., van Berckelaer, N., and Verhelst, M. (November, January 29). Minimum energy quantized neural networks. Proceedings of the 2017 51st Asilomar Conference on Signals, Systems, and Computers ACSSC 2017, Pacific Grove, CA, USA. · DOI
- Xu, C., Kirk, S.R., and Jenkins, S. (2009, January 26–28). Tiling for performance tuning on different models of GPUs. Proceedings of the 2009 Second International Symposium on Information Science and Engineering ISISE 2009, Shanghai, China. · DOI
- Sun, F., Li, X., Wang, Q., and Tang, C. (December, January 30). FPGA-based embedded system design. Proceedings of the IEEE Asia-Pacific Conference Circuits Systems APCCAS, Macao, China.
- Roth, W., Schindler, G., Zöhrer, M., Pfeifenberger, L., Peharz, R., Tschiatschek, S., Fröning, H., Pernkopf, F., and Ghahramani, Z. (2021, March 27). Resource-Efficient Neural Networks for Embedded Systems. Available online: http://arxiv.org/abs/2001.03048. · arXiv
- Courbariaux, M., Bengio, Y., and David, J.P. (2021, February 10). Low Precision Storage for Deep Learning. Available online: http://arxiv.org/abs/1511.00363%5Cnhttp://arxiv.org/abs/1412.7024. · arXiv
- Tong, 2000, Reducing power by optimizing the necessary precision/range of floating-point arithmetic, IEEE Trans. Very Large Scale Integr. Syst., 8, 273, 10.1109/92.845894 · doi:10.1109/92.845894
- Tagliavini, G., Mach, S., Rossi, D., Marongiu, A., and Benin, L. (2018, January 19–23). A transprecision floating-point platform for ultra-low power computing. Proceedings of the 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), Dresden, Germany. · doi:10.23919/date.2018.8342167
- Langroudi, S.H.F., Pandit, T., and Kudithipudi, D. (2018, January 25–25). Deep Learning inference on embedded devices: Fixed-point vs posit. Proceedings of the 2018 1st Workshop on Energy Efficient Machine Learning and Cognitive Computing for Embedded Applications (EMC2), Williamsburg, VA, USA.
- Hwang, K., and Sung, W. (2014, January 20–22). Fixed-point feedforward deep neural network design using weights +1, 0, and −1. Proceedings of the 2014 IEEE Workshop on Signal Processing Systems (SiPS), Belfast, UK. · DOI · Paper page
- Gustafson, 2017, Beating floating point at its own game: Posit arithmetic, Supercomput. Front. Innov., 4, 71
- Hammerstrom, D. (1990, January 17–21). A VLSI architecture for high-performance, low-cost, on-chip learning. Proceedings of the IJCNN. International JT Conference Neural Network, San Diego, CA, USA. · DOI · Paper page
- Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., and Bengio, Y. (2021, January 22). Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or −1. Available online: http://arxiv.org/abs/1602.02830. · arXiv
- Meng, W., Gu, Z., Zhang, M., and Wu, Z. (2021, February 03). Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices. Available online: http://arxiv.org/abs/1701.00485. · arXiv
- Park, E., Ahn, J., and Yoo, S. (2017, January 21–26). Weighted-entropy-based quantization for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. · DOI · Paper page
- Burrascano, 1991, Learning vector quantization for the probabilistic neural network, IEEE Trans. Neural Netw., 2, 458, 10.1109/72.88165 · doi:10.1109/72.88165
- Mittal, A., Tiku, S., and Pasricha, S. (2018, January 23–25). Adapting convolutional neural networks for indoor localization with smart mobile devices. Proceedings of the 2018 on Great Lakes Symposium on VLSI, 2018; GLSVLSI’18, Chicago, IL, USA. · DOI
- Hu, R., Tian, B., Yin, S., and Wei, S. (2018, January 19–21). Efficient hardware architecture of softmax layer in deep neural network. Proceedings of the 2018 IEEE 23rd International Conference on Digital Signal Processing (DSP), Shanghai, China. · DOI
- Hennessy, 2019, A new golden age for computer architecture, Commun. ACM, 62, 48, 10.1145/3282307 · DOI · Paper page
- Kim, 2018, Machine learning and manycore systems design: A Serendipitous symbiosis, Computer, 51, 66, 10.1109/MC.2018.3011040 · DOI
- Kim, R.G., Doppa, J.R., and Pande, P.P. (2018, January 5–8). Machine learning for design space exploration and optimization of manycore systems. Proceedings of the 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), San Diego, CA, USA. · DOI
- Vazquez, R., Gordon-Ross, A., and Stitt, G. (2019, January 21–24). Machine learning-based prediction for dynamic architectural optimizations. Proceedings of the 10th International Green and Sustainability Computing Conference IGSC 2019, Alexandria, VA, USA. · DOI
- Papp, D., Ma, Z., and Buttyan, L. (2015, January 21–23). Embedded systems security: Threats, vulnerabilities, and attack taxonomy. Proceedings of the 2015 13th Annual Conference on Privacy, Security and Trust (PST), Izmir, Turkey. · DOI · Paper page
- Ogbebor, 2020, Energy Efficient Design Techniques in Next-Generation Wireless Communication Networks: Emerging Trends and Future Directions, Wirel. Commun. Mob. Comput., 2020, 19, 10.1155/2020/7235362 · DOI
- Imoize, 2021, Standard Propagation Channel Models for MIMO Communication Systems, Wirel. Commun. Mob. Comput., 2021, 36, 10.1155/2021/8838792 · DOI
- Popoola, 2019, Determination of neural network parameters for path loss prediction in very high frequency wireless channel, IEEE Access, 7, 150462, 10.1109/ACCESS.2019.2947009 · DOI
- Faruk, 2019, Path loss predictions in the VHF and UHF bands within urban environments: Experimental investigation of empirical, heuristics and geospatial models, IEEE Access, 7, 77293, 10.1109/ACCESS.2019.2921411 · doi:10.1109/access.2019.2921411
- Pasricha, 2020, A Survey of Silicon Photonics for Energy-Efficient Manycore Computing, IEEE Des. Test, 37, 60, 10.1109/MDAT.2020.2982628 · DOI
- Soref, 2006, The past, present, and future of silicon photonics, IEEE J. Sel. Top. Quantum Electron., 12, 1678, 10.1109/JSTQE.2006.883151 · DOI · Paper page
- Chittamuru, 2018, BiGNoC: Accelerating big data computing with application-specific photonic network-on-chip architectures, IEEE Trans. Parallel Distrib. Syst., 29, 2402, 10.1109/TPDS.2018.2833876 · doi:10.1109/tpds.2018.2833876
Cited by
A Review of Embedded Machine Learning Based on Hardware, Application, and Sensing Scheme
Biglari, A., & Tang, W. (2023) · Sensors · doi:10.3390/s23042131 · Cited by 86
A TinyML Soft-Sensor Approach for Low-Cost Detection and Monitoring of Vehicular Emissions
Andrade, P., Silva, I., Silva, M., Flores, T., Cassiano, J., & Costa, D. G. (2022) · Sensors · doi:10.3390/s22103838 · Cited by 66
Mazzi, Y., Ben Sassi, H., Gaga, A., & Errahimi, F. (2022) · International Journal of Energy Research · doi:10.1002/er.7713 · Cited by 53
“42 This is been verified in Reference 43 where the authors investigated the performance of decision tree (DT), k-nearest neighbors (KNN), and SVM implemented on an STM32 Nucleo board.”
MethodA collective AI via lifelong learning and sharing at the edge
Soltoggio, A., Ben-Iwhiwhu, E., Braverman, V., Eaton, E., Epstein, B., Ge, Y., Halperin, L., How, J., Itti, L., Jacobs, M. A., et al. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00800-2 · Cited by 51
Salazar, C., Gonzalez-Llorente, J., Cardenas, L., Mendez, J., Rincon, S., Rodriguez-Ferreira, J., & Acero, I. F. (2022) · Remote Sensing · doi:10.3390/rs14215597 · Cited by 27
Metadata
- Authors
- Ajani, T. S., Imoize, A. L., & Atayero, A. A.
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2021-06-28
- Volume
- 21
- Issue
- 13
- Pages
- 4412
- ISSN
- 1424-8220 (ISSN-L)
- OpenAlex
- W3175915085
- Cited by
- 176
- References
- 24
- FWCI
- 9.61
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.