http://hdl.handle.net/10453/35203 2026-04-12T07:31:20Z http://hdl.handle.net/10453/171149 Title: Optimizing deep neural networks to predict the effect of social distancing on COVID-19 spread. Authors: Liu, D; Ding, W; Dong, ZS; Pedrycz, W Abstract: Deep Neural Networks (DNN) form a powerful deep learning model that can process unprecedented volumes of data. The hyperparameters of DNN have a significant influence on its prediction performance. Evolutionary algorithms (EAs) form a heuristic-based approach that provides an opportunity to optimize deep learning models to obtain good performance. Therefore, we propose an evolutionary deep learning model called IPSO-DNN based on DNN for prediction and an improved Particle Swarm Optimization (IPSO) algorithm to optimize the kernel hyperparameters of DNN in a self-adaptive evolutionary way. In the IPSO algorithm, a micro population size setting is introduced to improve the search efficiency of the algorithm, and the generalized opposition-based learning strategy is used to guide the population evolution. In addition, the IPSO algorithm employs a self-adaptive update strategy to prevent premature convergence and then improves the exploitation and exploration parameter optimization performance of DNN. In this paper, we show that the IPSO algorithm provides an efficient approach for tuning the hyperparameters of DNN with saving valuable computational resources. We explore the proposed IPSO-DNN model to predict the effect of social distancing on the spread of COVID-19 based on the social distancing metrics. The preliminary experimental results reveal that the proposed IPSO-DNN model has the least computation cost and yields better prediction accuracy results when compared to the other models. The experiments of the IPSO-DNN model also illustrate that aggressive and extensive social distancing interventions are crucial to help flatten the COVID-19 epidemic curve in the United States. 2022-04-01T00:00:00Z http://hdl.handle.net/10453/156735 Title: Evolutionary Deep Fusion Method and its Application in Chemical Structure Recognition Authors: Liang, X; Guo, Q; Qian, Y; Ding, W; Zhang, Q Abstract: Feature extraction is a critical issue in many machine learning systems. A number of basic fusion operators have been proposed and studied. This article proposes an evolutionary algorithm, called evolutionary deep fusion method, for searching an optimal combination scheme of different basic fusion operators to fuse multiview features. We apply our proposed method to chemical structure recognition. Our proposed method can directly take images as inputs, and users do not need to transform images to other formats. The experimental results demonstrate that our proposed method can achieve a better performance than those designed by human experts on this real-life problem. 2021-03-09T00:00:00Z http://hdl.handle.net/10453/146663 Title: Thorax disease classification with attention guided convolutional neural network Authors: Guan, Q; Huang, Y; Zhong, Z; Zheng, Z; Zheng, L; Yang, Y Abstract: © 2019 Elsevier B.V. This paper considers the task of thorax disease diagnosis on chest X-ray (CXR) images. Most existing methods generally learn a network with global images as input. However, thorax diseases usually happen in (small) localized areas which are disease specific. Thus training CNNs using global images may be affected by the (excessive) irrelevant noisy areas. Besides, due to the poor alignment of some CXR images, the existence of irregular borders hinders the network performance. For addressing the above problems, we propose to integrate the global and local cues into a three-branch attention guided convolution neural network (AG-CNN) to identify thorax diseases. An attention guided mask inference based cropping strategy is proposed to avoid noise and improve alignment in the global branch. AG-CNN also integrates the global cues to compensate the lost discriminative cues by the local branch. Specifically, we first learn a global CNN branch using global images. Then, guided by the attention heatmap generated from the global branch, we infer a mask to crop a discriminative region from the global image. The local region is used for training a local CNN branch. Lastly, we concatenate the last pooling layers of both the global and local branches for fine-tuning the fusion branch. Experiments on the ChestX-ray14 dataset demonstrate that after integrating the local cues with the global information, the average AUC scores are improved by AG-CNN. 2020-03-01T00:00:00Z http://hdl.handle.net/10453/141158 Title: Security and Cost-Aware Computation Offloading via Deep Reinforcement Learning in Mobile Edge Computing Authors: Huang, B; Li, Y; Li, Z; Pan, L; Wang, S; Xu, Y; Hu, H Abstract: © 2019 Binbin Huang et al. With the explosive growth of mobile applications, mobile devices need to be equipped with abundant resources to process massive and complex mobile applications. However, mobile devices are usually resource-constrained due to their physical size. Fortunately, mobile edge computing, which enables mobile devices to offload computation tasks to edge servers with abundant computing resources, can significantly meet the ever-increasing computation demands from mobile applications. Nevertheless, offloading tasks to the edge servers are liable to suffer from external security threats (e.g., snooping and alteration). Aiming at this problem, we propose a security and cost-aware computation offloading (SCACO) strategy for mobile users in mobile edge computing environment, the goal of which is to minimize the overall cost (including mobile device's energy consumption, processing delay, and task loss probability) under the risk probability constraints. Specifically, we first formulate the computation offloading problem as a Markov decision process (MDP). Then, based on the popular deep reinforcement learning approach, deep Q-network (DQN), the optimal offloading policy for the proposed problem is derived. Finally, extensive experimental results demonstrate that SCACO can achieve the security and cost efficiency for the mobile user in the mobile edge computing environment. 2019-01-01T00:00:00Z