Abstract
Model data-driven ontology and knowledge presentation for evolving semantic Asian social networks (OK-ASN) is a critical strategy for web of things (WoT) services. Meanwhile, Deep Neural Network (DNN)-based OK-ASN service in WoT is growing rapidly. However, most DNN-based services cannot utilize the potential of WoT fully, as heterogeneity exists in WoT. Therefore, this article proposes a novel framework called Web-based Heterogeneous Hierarchical Distributed Deep Neural Network (WH2D2N2) to deploy the DNNs for OK-ASN services on WoT, overcoming the heterogeneity. The architecture of the system and the designed Edge-Cloud-Joint execute scheme utilize heterogeneous devices to make DNN inference ubiquitous and output two types of results to meet various requirements. To bring robustness to OK-ASN services, a global scheduling is designed to arrange the workflow dynamically. The results of our experiments prove the efficiency of the execute scheme and the global scheduling in the system.
- [1] . 2014. Convolutional neural networks for speech recognition. IEEE/ACM Trans. Audio, Speech, Lang. Process. 22, 10 (2014), 1533–1545.Google Scholar
Digital Library
- [2] . 2022. Leveraging multilingual news websites for building a Kurdish parallel corpus. ACM Trans. Asian Low-Resour. Lang. Info. Process. (2022).Google Scholar
Digital Library
- [3] . 2020. Subword attentive model for arabic sentiment analysis: A deep learning approach. ACM Trans. Asian Low-Resour. Lang. Info. Process. 19, 2 (2020), 1–17.Google Scholar
Digital Library
- [4] . 2020. YOLOv4: Optimal speed and accuracy of object detection. Retrieved from https://arXiv:2004.10934.Google Scholar
- [5] . 2022. An edge intelligence empowered flooding process prediction using Internet of things in smart city. J. Parallel Distrib. Comput. 165 (2022), 66–78.Google Scholar
Cross Ref
- [6] . 2021. Distributed computation offloading method based on deep reinforcement learning in ICV. Appl. Soft Comput. 103 (2021), 107108.Google Scholar
Digital Library
- [7] . 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or \(-1\). Retrieved from https://arXiv:1602.02830.Google Scholar
- [8] . 2019. JointDNN: An efficient training and inference engine for intelligent mobile cloud computing services. IEEE Trans. Mobile Comput. 20, 2 (2019), 565–576.Google Scholar
- [9] . 2011. The websocket protocol. https://www.rfc-editor.org/rfc/rfc6455.txt.Google Scholar
- [10] . 2022. A mutually supervised graph attention network for few-shot segmentation: The perspective of fully utilizing limited samples. IEEE Trans. Neural Netw. Learn. Syst. (2022).Google Scholar
- [11] . 2019. Transformative effects of IoT, blockchain and artificial intelligence on cloud computing: Evolution, vision, trends and open challenges. Internet Things 8 (2019), 100118.Google Scholar
Cross Ref
- [12] . 2019. OpenVINO deep learning workbench: Comprehensive analysis and tuning of neural networks inference. In Proceedings of the IEEE International Conference on Computer Vision Workshops. 0–0.Google Scholar
- [13] . 2019. Generating titles for web tables. In Proceedings of the World Wide Web Conference. 638–647.Google Scholar
Digital Library
- [14] . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.Google Scholar
Cross Ref
- [15] . 2017. Webdnn: Fastest dnn execution framework on web browser. In Proceedings of the 25th ACM International Conference on Multimedia. 1213–1216.Google Scholar
Digital Library
- [16] . 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. Retrieved from https://arXiv:1704.04861.Google Scholar
- [17] . 2020. DeepAdapter: A collaborative deep learning framework for the mobile web using context-aware network pruning. In Proceedings of the IEEE INFOCOM Conference on Computer Communications. IEEE, 834–843.Google Scholar
Digital Library
- [18] . 2021. A hybrid CNN-LSTM: A deep learning approach for consumer sentiment analysis using qualitative user-generated contents. Trans. Asian Low-Resour. Lang. Info. Process. 20, 5 (2021), 1–15.Google Scholar
Digital Library
- [19] . 2009. Learning multiple layers of features from tiny images. (2009).Google Scholar
- [20] . 2020. SPINN: Synergistic progressive inference of neural networks over device and cloud. In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking. 1–15.Google Scholar
Digital Library
- [21] . 2017. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4681–4690.Google Scholar
Cross Ref
- [22] . 2018. Edge intelligence: On-demand deep learning model co-inference with device-edge synergy. In Proceedings of the Workshop on Mobile Edge Communications. 31–36.Google Scholar
- [23] . 2021. FedCPF: An efficient-communication federated learning approach for vehicular edge computing in 6G communication networks. IEEE Trans. Intell. Transport. Syst. 23, 2 (2021), 1616–1629.Google Scholar
Digital Library
- [24] . 2021. Federated-learning-based anomaly detection for IoT security attacks. IEEE Internet Things J. 9, 4 (2021), 2545–2554.Google Scholar
Cross Ref
- [25] . 2020. Semantic interoperability in the IoT: Extending the web of things architecture. ACM Trans. Internet Things 1, 1 (2020), 1–25.Google Scholar
Digital Library
- [26] . 2015. Deepid-net: Deformable deep convolutional neural networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2403–2412.Google Scholar
Cross Ref
- [27] . 2019. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems. 8026–8037.Google Scholar
- [28] . 2018. From raw data to smart manufacturing: AI and semantic web of things for industry 4.0. IEEE Intell. Syst. 33, 4 (2018), 79–86.Google Scholar
Digital Library
- [29] . 2019. SWAT: Seamless web authentication technology. In Proceedings of the World Wide Web Conference. 1579–1589.Google Scholar
Digital Library
- [30] . 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4510–4520.Google Scholar
Cross Ref
- [31] . 2018. A purely end-to-end system for multi-speaker speech recognition. Retrieved from https://arXiv:1805.05826.Google Scholar
- [32] . 2019. Tensorflow.js: Machine learning for the web and beyond. Retrieved from https://arXiv:1901.05350.Google Scholar
- [33] . 2018. OpenCV. js: Computer vision processing for the open web platform. In Proceedings of the 9th ACM Multimedia Systems Conference. 478–483.Google Scholar
Digital Library
- [34] . 2016. Branchynet: Fast inference via early exiting from deep neural networks. In Proceedings of the 23rd International Conference on Pattern Recognition (ICPR’16). IEEE, 2464–2469.Google Scholar
Cross Ref
- [35] . 2017. Distributed deep neural networks over the cloud, the edge and end devices. In Proceedings of the IEEE 37th International Conference on Distributed Computing Systems (ICDCS’17). IEEE, 328–339.Google Scholar
Cross Ref
- [36] . 2021. Multi-objective optimization for resource allocation in vehicular cloud computing networks. IEEE Trans. Intell. Transport. Syst. 23, 12 (2021), 25536–25545.Google Scholar
- [37] . 2017. Does that mean you’re happy? RNN-based modeling of user interaction sequences to detect good abandonment. In Proceedings of the ACM on Conference on Information and Knowledge Management. 727–736.Google Scholar
- [38] . 2018. Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6848–6856.Google Scholar
Cross Ref
- [39] . 2018. Towards ubiquitous intelligent computing: Heterogeneous distributed deep neural networks. IEEE Trans. Big Data 8, 3 (2018), 644–657.Google Scholar
Index Terms
WH2D2N2: Distributed AI-enabled OK-ASN Service for Web of Things
Recommendations
Interoperability of Security-Enabled Internet of Things
The future Internet will embrace the intelligence of Web 3.0 and the omnipresence of every day connected objects. The later was envisioned as the Internet of Things. Security and interoperability concerns are hindering the service innovations using the ...
Resolving heterogeneity of Web-service composition in network manufacturing based on ontology
Networked Manufacturing and Mass Customization in the ECommerce Era: the Chinese PerspectiveWeb-service composition provides more powerful service functions through integrating existing Web services on the Internet, and collaborative working and resource-sharing among enterprises on the Internet have become a popular trend by means of Web-...
Web service composition: a reality check
WISE'07: Proceedings of the 8th international conference on Web information systems engineeringAutomated web service composition is one of the major promises of service-oriented architecture, where services can be discovered and composed dynamically and automatically. To investigate the methods for composite web service construction, we conducted ...






Comments