Search

In this paper, nearly 40 commonly used deep neural network(DNN) models are selected, and their cross-platform and cross-inference frameworks are deeply analysed. The main metrics of accuracy, the total number of model parameters, the computational complexity, the accuracy density, the inference time, the memory consumption and other related parameters are used to measure their performance. The heterogeneous computing experiment is implemented on both the Google Colab cloud computing platform and the Jetson Nano embedded edge computing platform. The obtained performance is compared with that of two previous computing platforms: a workstation equipped with an NVIDIA Titan X Pascal and an embedded system based on an NVIDIA Jetson TX1 board. In addition, on the Jetson Nano embedded edge computing platform, different inference frameworks are investigated to evaluate the inference efficiency of the DNN models. Regression models are established to characterize the variation in the computing performance of different DNN classification algorithms so that the inference results of unknown models can be estimated. ANOVA methods are proposed to quantify the differences between models. The experimental results have important guiding significance for the better selection, deployment and application of DNN models in practice. Codes are available at this https URL https://github.com/Foreverzfy/Model-Test. [ABSTRACT FROM AUTHOR]

With the development of cloud technology, hierarchical and distributed cross-cloud architecture is gradually replacing traditional centralized architecture, for example, used in edge (or fog) computing. Due to the fluctuation of resource requirements, if a node does not have sufficient resources to process requests, the same or higher-level nodes can share their resources by offloading or redirecting requests to themselves, at the possible cost of reduced service quality. However, it is difficult to effectively optimize the sharing effect based on mean requirements. We formulate the multilevel problem with horizontal and vertical resource sharing using stochastic models, identify the optimal structures with embedded subproblems, and obtain the approximation solution in an efficient dynamic programming manner. In the problem setting with a wide range of different parameters, the proposed algorithm can outperform existing mean and heuristic algorithms in all scenarios to improve the total satisfied requirements by up to 26%, and can be hundreds of times faster than these heuristic algorithms. • The demand fluctuation in edge clouds is a new challenge for resource scheduling. • We formulate the general problem in hierarchical and distributed edge clouds. • The problem has non-linear object with non-linear constraints. • We identify the nested subproblems with their optimal condition. • The algorithm outperforms the existing mean and heuristic based algorithms. [ABSTRACT FROM AUTHOR]

The user demand increment and resource restrictions in IoT can provide efficient services without considering the service cost and service quality. Nowadays various computing technologies like fog, cloud, and edge computing and their confluence of IoT are required. The standard IoT services can be transformed into composite services via the incorporation of cloud computing with IoT. These IoT composite services are not suitable for various QoS scenarios which results in performance degradation and exhibited real-time adaptive sensing issues. Therefore, a novel Deep Q-learning Network-based Hybrid Enhanced Chimp Artificial Hummingbird (DQN-Hybrid ECAH) approach is proposed to overcome the state-of-art approach problems. The DQN-Hybrid ECAH approach represents a significant novelty in the field of IoT, as it utilizes a combination of advanced techniques to overcome the challenges posed by composite services in IoT. In particular, the use of deep Q-learning networks allows for the optimization of composite service quality, while the enhanced chimp artificial hummingbird techniques ensure that the approach is both efficient and effective. From the experimental evaluation, it is evident that the proposed approach is superior to other state-of-the-art methods. Specifically, the packet delivery ratio (PDF) and throughput rate obtained were high, with minimum jitter and average end-to-end delay. This demonstrates the effectiveness of the DQN-Hybrid ECAH approach in enhancing composite service quality in IoT applications. Overall, the proposed DQN-Hybrid ECAH approach represents a significant contribution to the field of IoT, providing a novel solution to the challenges associated with composite services in IoT. The approach has the potential to significantly improve the performance of IoT applications, while also reducing the real-time adaptive sensing issues that are often encountered in this context. [ABSTRACT FROM AUTHOR]

• This paper proposes a MOMHTS optimized HRFDL architecture for diagnosing the COVID-19 and pneumonia from chest CT and X-ray images via a collaborative edge framework to offer web services in underprivileged areas. • The hyperparameters of the HRFDL classifier are optimized using the MOMHTS algorithm which minimizes the complexity of the Deep learning model that prevents it from being deployed in the edge devices. COVID-19 is a global pandemic that mostly affects patients' respiratory systems, and the only way to protect oneself against the virus at present moment is to diagnose the illness, isolate the patient, and provide immunization. In the present situation, the testing used to predict COVID-19 is inefficient and results in more false positives. This difficulty can be solved by developing a remote medical decision support system that detects illness using CT scans or X-ray images with less manual interaction and is less prone to errors. The state-of-art techniques mainly used complex deep learning architectures which are not quite effective when deployed in resource-constrained edge devices. To overcome this problem, a Multi-Objective Modified Heat Transfer Search (MOMHTS) optimized Hybrid Random Forest Deep learning (HRFDL) classifier is proposed in this paper. The MOMHTS algorithm mainly optimizes the deep learning model in the HRFDL architecture by optimizing the hyperparameters associated with it to support the resource-constrained edge devices. To evaluate the efficiency of this technique, extensive experimentation is conducted on two real-time datasets namely the COVID19 lung CT scan dataset and the Chest X-ray images (Pneumonia) datasets. The proposed methodology mainly offers increased speed for communication between the IoT devices and COVID-19 detection via the MOMHTS optimized HRFDL classifier is modified to support the resources which can only support minimal computation and handle minimum storage. The proposed methodology offers an accuracy of 99% for both the COVID19 lung CT scan dataset and the Chest X-ray images (Pneumonia) datasets with minimal computational time, cost, and storage. Based on the simulation outcomes, we can conclude that the proposed methodology is an appropriate fit for edge computing detection to identify the COVID19 and pneumonia with higher detection accuracy. [ABSTRACT FROM AUTHOR]

Privacy-preserving Content-Based Image Retrieval (CBIR) method is a promising technology to achieve data confidentiality and searchability in cloud-assisted multimedia (i.e., image or video) data environment. However, inappropriate feature-preserving mechanisms and inefficient ciphertext descriptors resulted in lower performance than expected. Therefore, how to design encryption techniques with high security and how to extract effective features from ciphertext images still hinder privacy-preserving CBIR. For this goal, we propose a privacy-preserving image retrieval based on deep convolutional network features. First, a novel hybrid encryption technique is designed to encrypt images and an improved DenseNet model is fine-tuned by using the encrypted images to construct a feature extractor. The encrypted images and fine-tuning feature extractor are then uploaded to cloud server. Meanwhile, secure CBIR service is executed in the cloud server. We conduct experiments on two public benchmark datasets for performance evaluation in terms of mAP and accuracy. As demonstrated in the experimental results, the proposed method can achieve superior result compared with the existing methods, improving the performance on the two metrics by relatively 1.9% and 10%, respectively. Furthermore, the computational cost and parameters of depthwise separable convolution adopted by the improved DenseNet model are 8 to 9 times smaller than that of standard convolutions of the original DenseNet at only a small reduction in accuracy. • Preserving color features by replacing RGB channels. • The texture features are preserved by scrambling the pixel bit matrix. • A hybrid privacy-preserving mechanism for color and texture information. • The features of encrypted images are extracted by CNN on cloud server. • Experimental results show that our method is highly competitive. [ABSTRACT FROM AUTHOR]