SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System

As the advancement of deep learning (DL), the Internet of Things and cloud computing techniques for biomedical and healthcare problems, mobile healthcare systems have received unprecedented attention. Since DL techniques usually require enormous amount of computation, most of them cannot be directly deployed on the resource-constrained mobile and IoT devices. Hence, most of the mobile healthcare systems leverage the cloud computing infrastructure, where the data collected by the mobile and IoT devices would be transmitted to the cloud computing platforms for analysis. However, in the contested environments, relying on the cloud might not be practical at all times. For instance, the satellite communication might be denied or disrupted. We propose SAIA, a Split Artificial Intelligence Architecture for mobile healthcare systems. Unlike traditional approaches for artificial intelligence (AI) which solely exploits the computational power of the cloud server, SAIA could not only relies on the cloud computing infrastructure while the wireless communication is available, but also utilizes the lightweight AI solutions that work locally on the client side, hence, it can work even when the communication is impeded. In SAIA, we propose a meta-information based decision unit, that could tune whether a sample captured by the client should be operated by the embedded AI (i.e., keeping on the client) or the networked AI (i.e., sending to the server), under different conditions. In our experimental evaluation, extensive experiments have been conducted on two popular healthcare datasets. Our results show that SAIA consistently outperforms its baselines in terms of both effectiveness and efficiency.

[1]  Humberto Sossa,et al.  Quantitative evaluation of binary digital region asymmetry with application to skin lesion detection , 2018, BMC Medical Informatics and Decision Making.

[2]  Trevor Hastie,et al.  Multi-class AdaBoost ∗ , 2009 .

[3]  Verónica Vilaplana,et al.  BCN20000: Dermoscopic Lesions in the Wild , 2019, Scientific data.

[4]  Soo-Mook Moon,et al.  Computation Offloading for Machine Learning Web Apps in the Edge Server Environment , 2018, 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS).

[5]  Zhaozheng Yin,et al.  Lung segmentation in CT images using a fully convolutional neural network with multi-instance and conditional adversary loss , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[6]  Jun Zhang,et al.  Image Segmentation Based on 2D Otsu Method with Histogram Analysis , 2008, 2008 International Conference on Computer Science and Software Engineering.

[7]  J. Koenderink Q… , 2014, Les noms officiels des communes de Wallonie, de Bruxelles-Capitale et de la communaute germanophone.

[8]  Noel C. F. Codella,et al.  Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC) , 2019, ArXiv.

[9]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[10]  Philip S. Yu,et al.  Private Model Compression via Knowledge Distillation , 2018, AAAI.

[11]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Andreas Gerstlauer,et al.  DeepThings: Distributed Adaptive Deep Learning Inference on Resource-Constrained IoT Edge Clusters , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[13]  Quoc V. Le,et al.  Searching for MobileNetV3 , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[14]  R. Real,et al.  The Probabilistic Basis of Jaccard's Index of Similarity , 1996 .

[15]  Harald Kittler,et al.  Descriptor : The HAM 10000 dataset , a large collection of multi-source dermatoscopic images of common pigmented skin lesions , 2018 .

[16]  Trevor N. Mudge,et al.  Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge , 2017, ASPLOS.

[17]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[18]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  J. Morris Chang,et al.  Enhanced PeerHunter: Detecting Peer-to-Peer Botnets Through Network-Flow Level Community Behavior Analysis , 2018, IEEE Transactions on Information Forensics and Security.

[20]  Didrik Nielsen,et al.  Tree Boosting With XGBoost - Why Does XGBoost Win "Every" Machine Learning Competition? , 2016 .

[21]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[22]  M. Faezipour,et al.  Automated skin lesion analysis based on color and shape geometry feature set for melanoma early detection and prevention , 2014, IEEE Long Island Systems, Applications and Technology (LISAT) Conference 2014.

[23]  Hui Liu,et al.  On-Demand Deep Model Compression for Mobile Devices: A Usage-Driven Model Selection Framework , 2018, MobiSys.

[24]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[25]  Song Han,et al.  EIE: Efficient Inference Engine on Compressed Deep Neural Network , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

[26]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[27]  Matti Pietikäinen,et al.  Face Description with Local Binary Patterns: Application to Face Recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[29]  Seeja R D,et al.  Deep Learning Based Skin Lesion Segmentation and Classification of Melanoma Using Support Vector Machine (SVM) , 2019, Asian Pacific journal of cancer prevention : APJCP.

[30]  Li Fei-Fei,et al.  Progressive Neural Architecture Search , 2017, ECCV.

[31]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[33]  Gerhard Tutz,et al.  Boosting ridge regression , 2007, Comput. Stat. Data Anal..

[34]  Jianxin Wu,et al.  ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[35]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[36]  Hamed Haddadi,et al.  A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics , 2017, IEEE Internet of Things Journal.

[37]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[38]  Peter Buhlmann,et al.  BOOSTING ALGORITHMS: REGULARIZATION, PREDICTION AND MODEL FITTING , 2007, 0804.2752.

[39]  Zhiming Luo,et al.  Weighted Res-UNet for High-Quality Retina Vessel Segmentation , 2018, 2018 9th International Conference on Information Technology in Medicine and Education (ITME).

[40]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[41]  Nicholas D. Lane,et al.  DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices , 2016, 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

[42]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[43]  Eduardo Valle,et al.  Solo or Ensemble? Choosing a CNN Architecture for Melanoma Classification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[44]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[45]  Shuicheng Yan,et al.  Dual Path Networks , 2017, NIPS.

[46]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[47]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[48]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[49]  J. Friedman Stochastic gradient boosting , 2002 .

[50]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[52]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[53]  Sun-Yuan Kung,et al.  Cost-effective kernel ridge regression implementation for keystroke-based active authentication system , 2017, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[54]  Nam Phuong Nguyen,et al.  Gradient Boosting for Survival Analysis with Applications in Oncology , 2020 .

[55]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[56]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[57]  Rajesh Krishna Balan,et al.  DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications , 2017, MobiSys.

[58]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[59]  Pei-Yuan Wu,et al.  AutoGAN-based Dimension Reduction for Privacy Preservation , 2019, Neurocomputing.

[60]  Rich Caruana,et al.  Do Deep Nets Really Need to be Deep? , 2013, NIPS.

[61]  J. Morris Chang,et al.  PeerHunter: Detecting peer-to-peer botnets through community behavior analysis , 2017, 2017 IEEE Conference on Dependable and Secure Computing.

[62]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[63]  Torsten Hothorn,et al.  Identifying Risk Factors for Severe Childhood Malnutrition by Boosting Additive Quantile Regression , 2011 .

[64]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[65]  Woohyung Lim,et al.  Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network , 2018, PloS one.

[66]  Marco Levorato,et al.  Distilled Split Deep Neural Networks for Edge-Assisted Real-Time Systems , 2019, HotEdgeVideo@MOBICOM.

[67]  Dan Alistarh,et al.  Model compression via distillation and quantization , 2018, ICLR.

[68]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[69]  Sen Wang,et al.  FRiPAL: Face recognition in privacy abstraction layer , 2017, 2017 IEEE Conference on Dependable and Secure Computing.

[70]  D SeejaR,et al.  Deep Learning Based Skin Lesion Segmentation and Classification of Melanoma Using Support Vector Machine (SVM) , 2019 .

[71]  Chi-Wing Fu,et al.  H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes , 2018, IEEE Transactions on Medical Imaging.

[72]  Ran Gilad-Bachrach,et al.  DART: Dropouts meet Multiple Additive Regression Trees , 2015, AISTATS.