Search

Abstract The rise of 5G technology has driven the development of edge computing. Computation offloading is the key and challenging point in edge computing, which investigates offloading resource-intensive computing tasks from the user side to the cloud or edge side for processing. More consideration needs to be given to load balancing, user variability, and the heterogeneity of edge facilities in relevant research. In addition, most of the research around edge collaboration also revolves around cloud-side collaboration, which pays relatively little attention to the collaboration process between edge nodes, and the incentive and trust issues of the collaboration process need to be addressed. In this paper, we consider the impact of the user demand variability and the edge facility heterogeneity, then propose a method based on Vickrey-Clarke-Groves (VCG) auction theory to accommodate the edge demand response (EDR) process where the number of users and service facilities do not match. The method makes users’ bidding rules satisfy the Nash equilibrium and weakly dominant strategy, which can improve the load balancing of edge nodes, has positive significance in improving the edge resource utilization and reducing the system energy consumption. In particular, combined with blockchain, we further optimize the incentive and trust mechanism of edge collaboration and consider three scenarios: no collaboration, internal collaboration, and incentive collaboration. We also consider the impact of the user task’s transmission distance on the quality of experience (QoE). In addition, we illustrate the possible forking attack of blockchain in collaborative edge computing and propose a solution. We test the performance of the proposed algorithm on a real-world dataset, and the experimental results verify the algorithm’s effectiveness and the edge collaboration’s necessity.

Summary: To investigate whole-slide-level prediction in the field of artificial intelligence identification of dMMR/pMMR from hematoxylin and eosin (H&E) in colorectal cancer (CRC), we established a segmentation-based dMMR/pMMR deep learning detector (SPEED). Our model was approximately 1,700 times faster than that of the classification-based model. For the internal validation cohort, our model yielded an overall AUC of 0.989. For the external validation cohort, the model exhibited a high performance, with an AUC of 0.865. The human‒machine strategy further improved the model performance for external validation by an AUC up to 0.988. Our whole-slide-level prediction model provided an approach for dMMR/pMMR detection from H&E whole slide images with excellent predictive performance and less computer processing time in patients with CRC.

Bacterial blight poses a threat to rice production and food security, which can be controlled through large-scale breeding efforts toward resistant cultivars. Unmanned aerial vehicle (UAV) remote sensing provides an alternative means for the infield phenotype evaluation of crop disease resistance to relatively time-consuming and laborious traditional methods. However, the quality of data acquired by UAV can be affected by several factors such as weather, crop growth period, and geographical location, which can limit their utility for the detection of crop disease and resistant phenotypes. Therefore, a more effective use of UAV data for crop disease phenotype analysis is required. In this paper, we used time series UAV remote sensing data together with accumulated temperature data to train the rice bacterial blight severity evaluation model. The best results obtained with the predictive model showed an Rp2 of 0.86 with an RMSEp of 0.65. Moreover, model updating strategy was used to explore the scalability of the established model in different geographical locations. Twenty percent of transferred data for model training was useful for the evaluation of disease severity over different sites. In addition, the method for phenotypic analysis of rice disease we built here was combined with quantitative trait loci (QTL) analysis to identify resistance QTL in genetic populations at different growth stages. Three new QTLs were identified, and QTLs identified at different growth stages were inconsistent. QTL analysis combined with UAV high-throughput phenotyping provides new ideas for accelerating disease resistance breeding.

Echinochloa is an important genus in the grass family as many of them are either problematic weeds or domesticated millets. Here, the authors assemble three polyploidy genomes in this genus using the diploid-assisted scaffolding method DipHic and provide genomic insights into the dual roles of some species as weeds and orphan crops.

Hyperspectral imaging technique combined with machine learning is a powerful tool for the evaluation of disease phenotype in rice disease-resistant breeding. However, the current studies are almost carried out in the lab environment, which is difficult to apply to the field environment. In this paper, we used visible/near-infrared hyperspectral images to analysis the severity of rice bacterial blight (BB) and proposed a novel disease index construction strategy (NDSCI) for field application. A designed long short-term memory network with attention mechanism could evaluate the BB severity robustly, and the attention block could filter important wavelengths. Best results were obtained based on the fusion of important wavelengths and color features with an accuracy of 0.94. Then, NSDCI was constructed based on the important wavelength and color feature related to BB severity. The correlation coefficient of NDSCI extended to the field data reached -0.84, showing good scalability. This work overcomes the limitations of environmental conditions and sheds new light on the rapid measurement of phenotype in disease-resistant breeding.

With the development of medical technology, image semantic segmentation is of great significance for morphological analysis, quantification, and diagnosis of human tissues. However, manual detection and segmentation is a time-consuming task. Especially for biomedical image, only experts are able to identify tissues and mark their contours. In recent years, the development of deep learning has greatly improved the accuracy of computer automatic segmentation. This paper proposes a deep learning image semantic segmentation network named Spatial-Channel Attention U-Net (SCAU-Net) based on current research status of medical image. SCAU-Net has an encoder-decoder-style symmetrical structure integrated with spatial and channel attention as plug-and-play modules. The main idea is to enhance local related features and restrain irrelevant features at the spatial and channel levels. Experiments on the gland dataset GlaS and CRAG show that the proposed SCAU-Net model is superior to the classic U-Net model in image segmentation task, with 1% improvement on Dice score and 1.5% improvement on Jaccard score.

Background: Prediction models for the overall survival of pancreatic cancer remain unsatisfactory. We aimed to explore artificial neural networks (ANNs) modeling to predict the survival of unresectable pancreatic cancer patients.Methods: Thirty-two clinical parameters were collected from 221 unresectable pancreatic cancer patients, and their prognostic ability was evaluated using univariate and multivariate logistic regression. ANN and logistic regression (LR) models were developed on a training group (168 patients), and the area under the ROC curve (AUC) was used for comparison of the ANN and LR models. The models were further tested on the testing group (53 patients), and k-statistics were used for accuracy comparison.Results: We built three ANN models, based on 3, 7, and 32 basic features, to predict 8 month survival. All 3 ANN models showed better performance, with AUCs significantly higher than those from the respective LR models (0.811 vs. 0.680, 0.844 vs. 0.722, 0.921 vs. 0.849, all p < 0.05). The ability of the ANN models to discriminate 8 month survival with higher accuracy than the respective LR models was further confirmed in 53 consecutive patients.Conclusion: We developed ANN models predicting the 8 month survival of unresectable pancreatic cancer patients. These models may help to optimize personalized patient management.

The increasing number of Internet of Thing (IoT) devices and services makes it convenient for people to sense the real world and makes optimal decisions or complete complex tasks with them. However, the latency brought by unstable wireless networks and computation failures caused by constrained resources limit the development of IoT. A popular approach to solve this problem is to establish an IoT service provision system based on a mobile edge computing (MEC) model. In the MEC model, plenty of edge servers are placed with access points via wireless networks. With the help of cached services on edge servers, the latency can be reduced, and the computation can be offloaded. The cache services must be carefully selected so that many requests can by satisfied without overloading resources in edge servers. This paper proposes an optimized service cache policy by taking advantage of the composability of services to improve the performance of service provision systems. We conduct a series of experiments to evaluate the performance of our approach. The result shows that our approach can improve the average response time of these IoT services.

A mobile ad hoc network (MANET) can be constructed when a group of mobile users need to communicate temporarily in an ad hoc manner. It allows mobile services to be shared through device-to-device links and composed by combining a set of services together to create a complex, value-added, and cross-organizational business application. Nevertheless, various challenges, especially the reliability and quality-of-service of such a MANET-based mobile service composition, are yet to be properly tackled. Most studies and related composition strategies assume that mobile users are fully stable and constantly available. However, this is not realistic in most real-world scenarios where mobile users are mobile. The mobility of mobile users impact the reliability of corresponding mobile services and consequently impact the success rate of mobile service compositions. In this paper, we propose a reliability-aware mobile service composition approach based on prediction of mobile users' positions. We model the composition problem as a multi-objective optimization problem and develop an evolutionary multi-objective optimization-based algorithm to solve it. Extensive case studies are performed based on a real-world mobile users' trajectory data set and show that our proposed approach significantly outperforms traditional ones in terms of composition success rate.

Collaboration spaces formed from edge servers can efficiently improve the quality of experience of service subscribers. In this paper, we first utilize a strategy based on the density of Internet of Things (IoT) devices and k-means algorithm to partition network of edge servers, then an algorithm for IoT devices' computation offloading decisions is proposed, i.e., whether we need to offload IoT devices' workload to edge servers, and which edge server to choose if migration is needed. The combination of locations of edge servers and the geographic distribution of various IoT devices can significantly improve the scheduling of network resources and satisfy requirements of service subscribers. We analyze and build mathematical models about whether/how to offload tasks from various IoT devices to edge servers. In order to better simulate operations of the mobile edge servers in more realistic scenarios, the input size of each IoT device is uncertain and regarded as a random variable following some probability distribution based on long-term observations. On the basis of that, an algorithm utilizing sample average approximation method is proposed to discuss whether the tasks to be executed locally or offloaded. Besides, the algorithm proposed can also help decide whether service relocation/migration is needed or not. Finally, simulation results show that our algorithm can achieve 20% of global cost less than the benchmark on a true base station dataset of Hangzhou.